BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IDSS - ECPv6.0.5//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://idss.mit.edu
X-WR-CALDESC:Events for IDSS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221202T110000
DTEND;TZID=America/New_York:20221202T120000
DTSTAMP:20221206T054213
CREATED:20220720T165143Z
LAST-MODIFIED:20221122T160033Z
UID:16753-1669978800-1669982400@idss.mit.edu
SUMMARY:Coding convex bodies under Gaussian noise\, and the Wills functional
DESCRIPTION:Abstract:\nWe consider the problem of sequential probability assignment in the Gaussian setting\, where one aims to predict (or equivalently compress) a sequence of real-valued observations almost as well as the best Gaussian distribution with mean constrained to a general domain. First\, in the case of a convex constraint set K\, we express the hardness of the prediction problem (the minimax regret) in terms of the intrinsic volumes of K. We then establish a comparison inequality for the minimax regret in the general nonconvex case\, which underlines the metric nature of this quantity and generalizes the Slepian-Sudakov-Fernique comparison principle for the Gaussian width. Motivated by this inequality\, we present a sharp (up to universal constants) characterization of the considered functional for a general nonconvex set\, in terms of metric complexity measures. This implies isomorphic estimates for the log-Laplace transform of the intrinsic volume sequence of a convex body. We finally relate and contrast our findings with classical asymptotic results in information theory. \nBio:\nJaouad Mourtada is an Assistant Professor in the Department of Statistics at ENSAE/CREST. Prior to that\, he was a postdoctoral researcher at the Laboratory for Computational and Statistical Learning at the University of Genoa. He recieved his Ph.D. in the Center for Applied Mathematics (CMAP) at École Polytechnique. His research interests are at the intersection of statistics and learning theory\, specifically in understanding the complexity of prediction and estimation problems.
URL:https://idss.mit.edu/calendar/tbd-35/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221118T110000
DTEND;TZID=America/New_York:20221118T120000
DTSTAMP:20221206T054213
CREATED:20220720T164959Z
LAST-MODIFIED:20221110T133657Z
UID:16751-1668769200-1668772800@idss.mit.edu
SUMMARY:Distance-based summaries and modeling of evolutionary trees.
DESCRIPTION:Abstract: Phylogenetic trees are mathematical objects of great importance used to model hierarchical data and evolutionary relationships with applications in many fields including evolutionary biology and genetic epidemiology. Bayesian phylogenetic inference usually explore the posterior distribution of trees via Markov Chain Monte Carlo methods\, however assessing uncertainty and summarizing distributions remains challenging for these types of structures. In this talk I will first introduce a distance metric on the space of unlabeled ranked tree shapes and genealogies. I will then use it to define several summary statistics such as the Fréchet mean\, variance\, and interquartile sets. I will then provide an efficient combinatorial optimization algorithm for computation and show the applicability of our summaries for studying popular tree distributions and for comparing the SARS-CoV-2 evolutionary trees across different locations during the COVID-19 epidemic in 2020. \nBio: Dr. Julia A. Palacios is an Assistant Professor in the departments of Statistics\, Biomedical Data Science and by courtesy in Biology at Stanford University. Professor Palacios completed her PhD in Statistics at the University of Washington in 2013. She did a joint postdoc at Harvard University and Brown University before joining Stanford. In her research\, Professor Palacios seeks to provide statistically rigorous answers to concrete\, data-driven questions in population genetics\, epidemiology\, and comparative genomics\, often involving probabilistic modeling of evolutionary forces and the development of computationally tractable methods that are applicable to big data problems.
URL:https://idss.mit.edu/calendar/tbd-34/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221104T110000
DTEND;TZID=America/New_York:20221104T120000
DTSTAMP:20221206T054213
CREATED:20220720T164435Z
LAST-MODIFIED:20221026T123816Z
UID:16748-1667559600-1667563200@idss.mit.edu
SUMMARY:Inference in High Dimensions for (Mixed) Generalized Linear Models: the Linear\, the Spectral and the Approximate
DESCRIPTION:Abstract:\nIn a generalized linear model (GLM)\, the goal is to estimate a d-dimensional signal x from an n-dimensional observation of the form f(Ax\, w)\, where A is a design matrix and w is a noise vector. Well-known examples of GLMs include linear regression\, phase retrieval\, 1-bit compressed sensing\, and logistic regression. We focus on the high-dimensional setting in which both the number of measurements n and the signal dimension d diverge\, with their ratio tending to a fixed constant. Linear and spectral methods are two popular solutions to obtain an initial estimate\, which are also commonly used as a ‘warm start’ for other algorithms. In particular\, the linear estimator is a data-dependent linear combination of the columns of the design matrix\, and its analysis is quite simple; the spectral estimator is the principal eigenvector of a data-dependent matrix\, whose spectrum exhibits a phase transition. \nIn this talk\, I will start by discussing the emergence of this phase transition and provide precise asymptotics on the high-dimensional performance of the spectral method. Next\, I will show how to optimally combine the linear and spectral estimators. Finally\, I will add a ‘twist’ to the problem and consider the recovery of two signals from unlabeled data coming from a mixed GLM. Approximate message passing (AMP) algorithms (often used for high-dimensional inference tasks) will provide a powerful analytical tool to solve these problems. \nBio:\nMarco Mondelli received the B.S. and M.S. degree in Telecommunications Engineering from the University of Pisa\, Italy\, in 2010 and 2012\, respectively. In 2016\, he obtained his Ph.D. degree in Computer and Communication Sciences at the École Polytechnique Fédérale de Lausanne (EPFL)\, Switzerland. He is currently an Assistant Professor at the Institute of Science and Technology Austria (ISTA). Prior to that\, he was a Postdoctoral Scholar in the Department of Electrical Engineering at Stanford University\, USA\, from February 2017 to August 2019. He was also a Research Fellow with the Simons Institute for the Theory of Computing\, UC Berkeley\, USA\, for the program on Foundations of Data Science from August to December 2018. His research interests include data science\, machine learning\, information theory\, and modern coding theory. He was the recipient of a number of fellowships and awards\, including the Jack K. Wolf ISIT Student Paper Award in 2015\, the STOC Best Paper Award in 2016\, the EPFL Doctorate Award in 2018\, the Simons-Berkeley Research Fellowship in 2018\, the Lopez-Loreta Prize in 2019\, and Information Theory Society Best Paper Award in 2021.
URL:https://idss.mit.edu/calendar/tbd-33/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221028T110000
DTEND;TZID=America/New_York:20221028T120000
DTSTAMP:20221206T054213
CREATED:20220720T164210Z
LAST-MODIFIED:20221017T155942Z
UID:16745-1666954800-1666958400@idss.mit.edu
SUMMARY:Sampling from the SK measure via algorithmic stochastic localization
DESCRIPTION:Abstract: I will present an algorithm which efficiently samples from the Sherrington-Kirkpatrick (SK) measure with no external field at high temperature. \nThe approach is based on the stochastic localization process of Eldan\, together with a subroutine for computing the mean vectors of a family of SK measures tilted by an appropriate external field. This approach is general and can potentially be applied to other discrete or continuous non-log-concave problems. \n\nWe show that the algorithm outputs a sample within vanishing rescaled Wasserstein distance to the SK measure\, for all inverse temperatures beta < 1/2. In a recent development\, Celentano (2022) shows that our algorithm succeeds for all beta < 1\, i.e.\, in the entire high temperature phase. \nConversely\, we show that in the low temperature phase beta >1\, no ‘stable’ algorithm can approximately sample from the SK measure. In this case we show that the SK measure is unstable to perturbations in a certain sense. This settles the computational tractability of sampling from SK for all temperatures except the critical one. \nThis is based on a joint work with Andrea Montanari and Mark Sellke. \n\nBio: Ahmed El Alaoui joined the Statistics and Data Science faculty at Cornell University as an assistant professor in January 2021. He received his PhD in 2018 in Electrical Engineering and Computer Sciences from UC Berkeley\, advised by Michael I. Jordan. He was afterwards a postdoctoral researcher at Stanford University\, hosted by Andrea Montanari. He is currently a Simons-Berkeley research fellow at the Simons Institute for the Theory of Computing at UC Berkeley. His research interests revolve around high-dimensional phenomena in statistics and probability theory\, statistical physics\, algorithms\, and problems where these areas meet.
URL:https://idss.mit.edu/calendar/tbd-32/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221021T110000
DTEND;TZID=America/New_York:20221021T120000
DTSTAMP:20221206T054213
CREATED:20220720T163024Z
LAST-MODIFIED:20221013T183832Z
UID:16743-1666350000-1666353600@idss.mit.edu
SUMMARY:Maximum likelihood for high-noise group orbit estimation and cryo-EM
DESCRIPTION:Abstract: Motivated by applications to single-particle cryo-electron microscopy\, we study a problem of group orbit estimation where samples of an unknown signal are observed under uniform random rotations from a rotational group. In high-noise settings\, we show that geometric properties of the log-likelihood function are closely related to algebraic properties of the invariant algebra of the group action. Eigenvalues of the Fisher information matrix are stratified according to a sequence of transcendence degrees in this invariant algebra\, and critical points of the log-likelihood optimization landscape are in correspondence with those of a sequence of polynomial optimization problems. I will discuss the implications of this theory in several examples\, including a simplified model of cryo-EM. \nThe talk will be based on the papers arxiv.org/abs/2004.00041 and arxiv.org/abs/2107.01305\, joint work with Roy Lederman\, Yi Sun\, Tianhao Wang\, Yihong Wu\, and Sheng Xu. \nBio: Zhou Fan is an Assistant Professor in the Department of Statistics and Data Science at Yale University. His research is driven by the goals of understanding high-dimensional phenomena in statistics and machine learning\, developing computationally efficient algorithms for high-dimensional inference problems with structure\, and bridging theoretical advances in these areas with scientific applications. Recent interests include random matrix theory and free probability\, statistical physics and high-dimensional Bayesian inference\, and inferential problems arising in cryo-electron microscopy and statistical genetics.
URL:https://idss.mit.edu/calendar/tbd-31/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221007T110000
DTEND;TZID=America/New_York:20221007T120000
DTSTAMP:20221206T054213
CREATED:20220720T162338Z
LAST-MODIFIED:20220928T192151Z
UID:16739-1665140400-1665144000@idss.mit.edu
SUMMARY:Efficient derivative-free Bayesian inference for large-scale inverse problems
DESCRIPTION:Abstract:\nWe consider Bayesian inference for large-scale inverse problems\, where computational challenges arise from the need for the repeated evaluations of an expensive forward model\, which is often given as a black box or is impractical to differentiate. In this talk I will propose a new derivative-free algorithm Unscented Kalman Inversion\, which utilizes the ideas from Kalman filter\, to efficiently solve these inverse problems. First\, I will explain some basics about Variational Inference under general metric tensors. In particular\, under the Fisher-Rao metric\, the Gaussian Variational Inference leads to the natural gradient descent. Next\, I will discuss two different views of our algorithm. It can be obtained from a Gaussian approximation of the filtering distribution of a novel mean field dynamical system. And it can also be viewed as a derivative-free approximation of the natural gradient descent. I will also discuss theoretical properties for linear inverse problems. Finally\, I will discuss an extension of our algorithm using Gaussian mixture approximation\, which leads to the Gaussian Mixture Kalman Inversion\, an efficient derivative-free Bayesian inference approach capable of capturing multiple modes. I will demonstrate the effectiveness of this approach in several numerical experiments with multimodal posterior distributions\, which typically converge within O(10) iterations. This is based on joint works with Yifan Chen\, Daniel Zhengyu Huang\, Sebastian Reich and Andrew Stuart. \nBio:\nJiaoyang Huang is an Assistant Professor of Statistics and Data Science at the University of Pennsylvania. Before that he was a Simons Junior fellow and postdoc at Courant Institute NYU. He obtained a PhD in mathematics from Harvard University in 2019\, and a BS in Mathematics from MIT in 2014. His research interests include probability theory and its applications to problems from statistical physics\, combinatorics\, computer science and statistics.
URL:https://idss.mit.edu/calendar/tbd-29/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220930T110000
DTEND;TZID=America/New_York:20220930T120000
DTSTAMP:20221206T054213
CREATED:20220720T161456Z
LAST-MODIFIED:20220912T144226Z
UID:16737-1664535600-1664539200@idss.mit.edu
SUMMARY:Regularized modified log-Sobolev inequalities\, and comparison of Markov chains
DESCRIPTION:Abstract: In this work\, we develop a comparison procedure for the Modified log-Sobolev Inequality (MLSI) constants of two reversible Markov chains on a finite state space. As an application\, we provide a sharp estimate of the MLSI constant of the switch chain on the set of simple bipartite regular graphs of size n with a fixed degree d. Our estimate implies that the total variation mixing time of the switch chain is of order O(n log(n)). The result is optimal up to a multiple depending on d and resolves an old open problem. Based on joint work with Pierre Youssef. \nBio:\nKonstantin Tikhomirov is an Assistant Professor at the School of Mathematics at the Georgia Institute of Technology\, with interests in discrete probability\, combinatorics\, convex geometry\, and applications to data analysis.
URL:https://idss.mit.edu/calendar/tbd-28/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220916T110000
DTEND;TZID=America/New_York:20220916T120000
DTSTAMP:20221206T054213
CREATED:20220720T161120Z
LAST-MODIFIED:20220802T174919Z
UID:16734-1663326000-1663329600@idss.mit.edu
SUMMARY:Short Stories about Data and Sports
DESCRIPTION:ABSTRACT\nRecent advances in data collection have made sports an attractive testing ground for new analyses and algorithms\, and a fascinating controlled microcosm in which to explore social interactions. In this talk I will describe two studies in this arena: one related to public health and the pandemic and one related to decision-making in basketball. In the first\, I will discuss what can be learned from the natural experiments that were (fortuitously) run in America football stadiums. During the 2020 National Football League (NFL) season\, teams collaborated with local communities to determine whether or not to allow fans in the stadiums during the pandemic. These policy decisions were made based on local guidelines\, local prevalence of the virus\, community risk tolerance\, and other localized considerations; some stadiums ultimately decided to allow fans at the games while others remained closed\, providing perhaps the first set of natural experiments that can be analyzed to investigate the impact of opening stadiums on public health. In the second part of the talk\, I will discuss metrics to assess to the decision-making capability of athletes. In most professional sports\, it is well-known that physical ability is only one piece of the puzzle; cognitive aspects of the game\, including the ability to make sound decisions under pressure\, play an important role in athletic success. In many games\, these decisions manifest as physical actions that can be captured in tracking data. Here I will describe a framework to evaluate decision-making and to assess game strategy and execution efficacy. The framework is built on an Expected Possession Value (EPV) metric in basketball which is leveraged to identify scoring opportunities throughout a game.\n\n\n \n\nBIO:\nAnette “Peko” Hosoi is the Neil and Jane Pappalardo Professor of Mechanical Engineering\, Professor of Mathematics and a Faculty Member of the Institute for Data\, Systems\, and Society. Her research contributions lie at the junction of nonlinear hydrodynamics\, biomechanics\, and bio-inspired design. A common theme in her work is the fundamental study of shape\, kinematic\, and rheological optimization of biological systems with applications to the emergent field of soft robotics. More recently\, she has turned her attention to problems that lie intersection of biomechanics\, applied mathematics\, and sports. She is the co-founder of the MIT Sports Lab which connects the MIT community with pro-teams and industry partners to address data and engineering challenges that lie within the sports domain.\n\nPeko joined the Department of Mechanical Engineering in 2002 as an assistant professor after receiving an AB in physics from Princeton University and an MA and PhD in physics from the University of Chicago. She has received numerous awards including the APS Stanley Corrsin Award\, the Bose Award for Excellence in Teaching\, and the Jacob P. Den Hartog Distinguished Educator Award. She is a Fellow of the American Physical Society (APS)\, a Radcliffe Institute Fellow\, and a MacVicar Faculty Fellow.
URL:https://idss.mit.edu/calendar/tbd-27/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220909T110000
DTEND;TZID=America/New_York:20220909T120000
DTSTAMP:20221206T054213
CREATED:20220720T160625Z
LAST-MODIFIED:20220901T151218Z
UID:16731-1662721200-1662724800@idss.mit.edu
SUMMARY:Beyond UCB: statistical complexity and optimal algorithm for non-linear ridge bandits
DESCRIPTION:Abstract:\nMany existing literature on bandits and reinforcement learning assume a linear reward/value function\, but what happens if the reward is non-linear? Two curious phenomena arise for non-linear bandits: first\, in addition to the “learning phase” with a standard \Theta(\sqrt(T)) regret\, there is an “initialization phase” with a fixed cost determined by the reward function; second\, achieving the smallest cost of the initialization phase requires new learning algorithms other than traditional ones such as UCB. For a special family of non-linear bandits\, we derive upper and lower bounds on the optimal fixed cost\, and in addition\, on the entire learning trajectory in the initialization phase via differential equations. In particular\, we show that a two-stage algorithm which first finds a good initialization and then treats the problem as a locally linear bandit is statistically optimal. In contrast\, several classical algorithms\, such as UCB and algorithms relying on online regression oracles\, are provably suboptimal.\n\nThis is based on a recent joint work with Jiantao Jiao\, Nived Rajaraman\, and Kannan Ramchandran. \n\nBio:\nYanjun Han is a Norbert-Wiener postdoctoral fellow in the Statistics and Data Science Center\, mentored by Sasha Rakhlin and Philippe Rigollet. He received his Ph.D. in Electrical Engineering from Stanford University in Aug 2021\, under the supervision of Tsachy Weissman. After that\, he spent one year as a postdoctoral scholar at the Simons Institute for the Theory of Computing\, UC Berkeley. Starting from Sept 2023\, he will be an assistant professor of mathematics and data science at the Courant Institute of Mathematical Sciences and the Center for Data Science at NYU. His research interests lie in statistical machine learning\, high-dimensional and nonparametric statistics\, online learning and bandits\, and information theory.
URL:https://idss.mit.edu/calendar/tbd-26/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220506T110000
DTEND;TZID=America/New_York:20220506T120000
DTSTAMP:20221206T054213
CREATED:20220124T213354Z
LAST-MODIFIED:20220428T191240Z
UID:15698-1651834800-1651838400@idss.mit.edu
SUMMARY:Sampling rare events in Earth and planetary science
DESCRIPTION:Abstract: This talk will cover recent work in our group developing and applying algorithms to simulate rare events in atmospheric science and other areas. I will review a rare event simulation scheme that biases model simulations toward the rare event of interest by preferentially duplicating simulations making progress toward the event and removing others. I will describe applications of this approach to rapid intensification of tropical cyclones and instability of Mercury’s orbit with an emphasis on the elements of algorithm design that most affect performance.\n\nBio: Jonathan Weare is currently an associate professor of mathematics in the Courant Institute of Mathematical Sciences at New York University. Previously he was an associate professor in the statistics department and in the James Franck Institute at the University of Chicago and\, before that\, an assistant professor in the mathematics department there. Before moving to Chicago he was a Courant Instructor of mathematics at NYU and a PhD student in mathematics at the University of California at Berkeley.
URL:https://idss.mit.edu/calendar/weare/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220429T110000
DTEND;TZID=America/New_York:20220429T120000
DTSTAMP:20221206T054213
CREATED:20220124T211441Z
LAST-MODIFIED:20220413T140106Z
UID:15695-1651230000-1651233600@idss.mit.edu
SUMMARY:Is quantile regression a suitable method to understand tax incentives for charitable giving? Case study from the Canton of Geneva\, Switzerland
DESCRIPTION:Abstract: Under the current Swiss law\, taxpayers can deduct charitable donations from their individual’s taxable income subject to a 20%-ceiling. This deductible ceiling was increased at the communal and cantonal level from a previous 5%-ceiling in 2009. The goal of the reform was boosting charitable giving to non-profit entities. However\, the effects of this reform\, and more generally of the existing Swiss system of tax deductions for charitable giving has never been empirically studied. The aim of this work is to provide as many taxation insights and deducters characteristics as possible into both the effects of the 2009 reform\, as well as into the patterns of giving and deducting by different classes of deducters by income and wealth. \nUsing unique panel data\, shared by the Geneva Tax Administration\, for a time framework of 11 years: 2001-2011\, an in-depth statistical analysis was conducted. The overall taxpayers population has been described\, dividing them into six categories according to the income distribution. We studied the changes in the volume of deductions between categories. Quantile regressions models for each year has been fitted to underlying the different income behaviors toward deductions. Moreover\, a specific subset of deducters more sensitive to the deductible ceiling for their donations was identified and studied in detail. The overall net income\, gross wealth\, together with the year of birth\, were the main covariates of interest. Standard linear regression and robust regression models were performed and significant variables\, which help answering the questions of taxpayers’ charitable giving behavior\, were identified. \nIncome has resulted the most significant variable\, driving donations\, and robust regressions the statistical techniques better incorporating the data peculiarity\, without giving too much weight to outliers\, and with an excellent model fitting. This paper seeks to provide both Swiss and foreign academics and policymakers with new research and policy insights. \n– \nBios: Giedre Lideikyte Huber is a Senior lecturer at the Faculty of Law and a Swiss National Science Foundation researcher. She specializes in tax law\, and more specifically in taxation of philanthropy\, corporate taxation and sustainable tax systems (including gender and climate issues in taxation). She has received numerous academic awards and grants\, awarded by the Swiss National Science Foundation (FNS)\, the Fondation Zdenek et Michaela Bakala\, the University of Geneva (Subside Tremplin) and Centre Maurice Chalumeau en sciences des sexualités. (see more) \nMarta Pittavino is a Senior Lecturer and a Senior Research Associate at the Research Center for Statistics of the Geneva School of Economics and Management (GSEM)\, within the University of Geneva. She is scientific coordinator and manager of the Master of Science in Business Analytics. Marta holds a PhD in Biostatistics and Epidemiology from the University of Zurich. Before joining the GSEM\, she was a post-doctoral scientist\, applied statistician\, at the International Agency for Research on Cancer\, part of the World Health Organization\, in Lyon\, France. Her research interests lie in the applied statistics field: data analysis\, forecasting and regression methods\, with a focus on the development of Bayesian hierarchical models applied to epidemiological studies
URL:https://idss.mit.edu/calendar/lideikyte-huber/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220422T110000
DTEND;TZID=America/New_York:20220422T120000
DTSTAMP:20221206T054213
CREATED:20220124T210948Z
LAST-MODIFIED:20220422T092752Z
UID:15693-1650625200-1650628800@idss.mit.edu
SUMMARY:Learning with Random Features and Kernels: Sharp Asymptotics and Universality Laws
DESCRIPTION:Abstract: Many new random matrix ensembles arise in learning and modern signal processing. As shown in recent studies\, the spectral properties of these matrices help answer crucial questions regarding the training and generalization performance of neural networks\, and the fundamental limits of high-dimensional signal recovery. As a result\, there has been growing interest in precisely understanding the spectra and other asymptotic properties of these matrices. Unlike their classical counterparts\, these new random matrices are often highly structured and are the result of nonlinear transformations. This combination of structure and nonlinearity leads to substantial technical challenges when applying existing tools from random matrix theory to these new random matrix ensembles. \nIn this talk\, we will consider learning by random feature models and the related problem of kernel ridge regression. In each case\, a nonlinear random matrix plays a prominent role. We provide an exact characterization of the asymptotic training and generalization errors of these models. These results reveal the important roles played by the regularization\, the loss function and the activation function in the mitigation of the “double descent phenomenon” in learning. The asymptotic analysis is made possible by a general universality theorem\, which establishes the asymptotic equivalence between the nonlinear random matrices and a surrogate linear random matrix ensemble that is much easier to work with. \n– \nBio: Yue M. Lu attended the University of Illinois at Urbana-Champaign\, where he received the M.Sc. degree in mathematics and the Ph.D. degree in electrical engineering\, both in 2007. After his postdoctoral training at the Audiovisual Communications Laboratory at Ecole Polytechnique Fédérale de Lausanne (EPFL)\, Switzerland\, he joined Harvard University\, where he is currently Gordon McKay Professor of Electrical Engineering and of Applied Mathematics at the John A. Paulson School of Engineering and Applied Sciences. He is also fortunate to have held visiting appointments at Duke University in 2016 and at the École Normale Supérieure (ENS) in 2019. His research interests include theoretical and algorithmic aspects of high-dimensional signal and information processing. He is an IEEE Signal Processing Society Distinguished Lecturer and a recipient of the ECE Illinois Young Alumni Achievement Award. \n– \nA full schedule for Spring 2022 Stochastics and Statistics Seminars can be found here:https://stat.mit.edu/seminars/upcoming/
URL:https://idss.mit.edu/calendar/lu2/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220415T110000
DTEND;TZID=America/New_York:20220415T120000
DTSTAMP:20221206T054213
CREATED:20220124T210116Z
LAST-MODIFIED:20220411T135103Z
UID:15691-1650020400-1650024000@idss.mit.edu
SUMMARY:Causal Representation Learning – A Proposal
DESCRIPTION:Abstract: The development of CRISPR-based assays and small molecule screens holds the promise of engineering precise cell state transitions to move cells from one cell type to another or from a diseased state to a healthy state. The main bottleneck is the huge space of possible perturbations/interventions\, where even with the breathtaking technological advances in single-cell biology it will never be possible to experimentally perturb all combinations of thousands of genes or compounds. This important biological problem calls for a framework that can integrate data from different modalities to identify causal representations\, predict the effect of unseen interventions\, and identify the optimal interventions to induce precise cell state transition. Traditional representation learning methods\, although often highly successful in predictive tasks\, do not generally elucidate causal relationships. In this talk\, we will present initial ideas towards building a statistical and computational framework for causal representation learning and its application towards optimal intervention design. \n– \nBio: Caroline Uhler is the Henry L. and Grace Doherty associate professor in EECS and IDSS\, a member of SDSC\, LIDS and the ORC\, Machine Learning at MIT\, and is also core member of the Broad Institute\, where she co-directs the Eric and Wendy Schmidt Center. She is an elected member of the International Statistical Institute and the recipient of a Simons Investigator Award\, a Sloan Research Fellowship\, an NSF Career Award\, a Sofja Kovalevskaja Award from the Humboldt Foundation\, and a START Award from the Austrian Science Fund.
URL:https://idss.mit.edu/calendar/uhler/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220408T110000
DTEND;TZID=America/New_York:20220408T120000
DTSTAMP:20221206T054213
CREATED:20220124T205412Z
LAST-MODIFIED:20220331T125923Z
UID:15688-1649415600-1649419200@idss.mit.edu
SUMMARY:The query complexity of certification
DESCRIPTION:Abstract: We study the problem of certification: given queries to an n-variable boolean function f with certificate complexity k and an input x\, output a size-k certificate for f’s value on x. This abstractly models a problem of interest in explainable machine learning\, where we think of f as a blackbox model that we seek to explain the predictions of. \nFor monotone functions\, classic algorithms of Valiant and Angluin accomplish this task with n queries to f. Our main result is a new algorithm for certifying monotone functions with O(k^8 log(n)) queries\, which comes close to matching the information-theoretic lower bound of Omega(k log(n)). The design and analysis of our algorithm are based on a new connection to threshold phenomena in monotone functions. \nJoint work with Guy Blanc\, Caleb Koch\, and Jane Lange. Available at https://arxiv.org/abs/2201.07736. \n– \nBio: Li-Yang Tan is an assistant professor of computer science at Stanford. He is broadly interested in theoretical computer science\, with an emphasis on computational complexity. A main theme in his work is the development of techniques to understand boolean function complexity\, and the application of these techniques to a range of areas in theoretical computer science. His work has been recognized with best paper awards at FOCS and CCC.
URL:https://idss.mit.edu/calendar/tan/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220318T110000
DTEND;TZID=America/New_York:20220318T120000
DTSTAMP:20221206T054213
CREATED:20220124T205021Z
LAST-MODIFIED:20220314T121813Z
UID:15686-1647601200-1647604800@idss.mit.edu
SUMMARY:Mean-field approximations for high-dimensional Bayesian Regression
DESCRIPTION:Abstract:\nVariational approximations provide an attractive computational alternative to MCMC-based strategies for approximating the posterior distribution in Bayesian inference. Despite their popularity in applications\, supporting theoretical guarantees are limited\, particularly in high-dimensional settings. \nIn the first part of the talk\, we will study bayesian inference in the context of a linear model with product priors\, and derive sufficient conditions for the correctness (to leading order) of the naive mean-field approximation. To this end\, we will utilize recent advances in the theory of non-linear large deviations (Chatterjee and Dembo 2014). Next\, we analyze the naive mean-field variational problem\, and precisely characterize the asymptotic properties of the posterior distribution in this setting. \nIn the second part of the talk\, we will turn to linear regression with iid gaussian design under a proportional asymptotic setting. The naive mean- field approximation is conjectured to be inaccurate in this case|instead\, the Thouless-Anderson-Palmer approximation from statistical physics is expected to provide a tight approximation. We will rigorously establish the TAP formula under a uniform spherical prior on the regression coefficients. This is based on joint work with Sumit Mukherjee (Columbia University) and Jiaze Qiu (Harvard University). \n– \nBio:\nSubhabrata Sen is an assistant professor in the Department of Statistics\, Harvard University. His research interests span Applied Probability\, Statistics\, and Machine Learning. He was a Schramm postdoc at Microsoft Research New England and MIT Mathematics from 2017-2019. He graduated from the Stanford Statistics Department in 2017\, where he was jointly advised by Prof Amir Dembo and Prof Andrea Montanari. Prior to joining Stanford\, he received his undergraduate and Masters degrees in Statistics from the Indian Statistical Institute\, Kolkata.
URL:https://idss.mit.edu/calendar/sen/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220311T110000
DTEND;TZID=America/New_York:20220311T120000
DTSTAMP:20221206T054213
CREATED:20220124T204503Z
LAST-MODIFIED:20220302T145054Z
UID:15683-1646996400-1647000000@idss.mit.edu
SUMMARY:Inference on Winners
DESCRIPTION:Abstract: Many empirical questions concern target parameters selected through optimization. For example\, researchers may be interested in the effectiveness of the best policy found in a randomized trial\, or the best-performing investment strategy based on historical data. Such settings give rise to a winner’s curse\, where conventional estimates are biased and conventional confidence intervals are unreliable. This paper develops optimal confidence intervals and median-unbiased estimators that are valid conditional on the target selected and so overcome this winner’s curse. If one requires validity only on average over targets that might have been selected\, we develop hybrid procedures that combine conditional and projection confidence intervals to offer further performance gains relative to existing alternatives. \nBio: Isaiah Andrews is a Professor of Economics at Harvard University\, a Research Associate at the National Bureau of Economic Research (NBER)\, a fellow of the Econometric Society\, and a co-editor at the American Economic Review. He specializes in econometrics\, and his research focuses on developing methods for inference that are robust to common problems in empirical work\, including insufficiently informative data (weak identification) and model misspecification. He received a MacArthur fellowship in 2020 and the John Bates Clark Medal in 2021.
URL:https://idss.mit.edu/calendar/andrews/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220304T110000
DTEND;TZID=America/New_York:20220304T120000
DTSTAMP:20221206T054213
CREATED:20220304T141324Z
LAST-MODIFIED:20220304T141437Z
UID:16039-1646391600-1646395200@idss.mit.edu
SUMMARY:Optimal testing for calibration of predictive models
DESCRIPTION:Abstract: The prediction accuracy of machine learning methods is steadily increasing\, but the calibration of their uncertainty predictions poses a significant challenge. Numerous works focus on obtaining well-calibrated predictive models\, but less is known about reliably assessing model calibration. This limits our ability to know when algorithms for improving calibration have a real effect\, and when their improvements are merely artifacts due to random noise in finite datasets. In this work\, we consider the problem of detecting mis-calibration of predictive models using a finite validation dataset. Due to the randomness in the data\, plug-in measures of calibration need to be compared against a proper background distribution to reliably assess calibration. Thus\, detecting mis-calibration in a classification setting can be formulated as a statistical hypothesis testing problem. The null hypothesis is that the model is perfectly calibrated\, while the alternative hypothesis is that the deviation from calibration is sufficiently large. \nWe find that detecting mis-calibration is only possible when the conditional probabilities of the classes are sufficiently smooth functions of the predictions. When the conditional class probabilities are H\”older continuous\, we propose a minimax optimal test for calibration based on a debiased plug-in estimator of the $\ell_2$-Expected Calibration Error (ECE). We further propose a version that is adaptive to unknown smoothness. We verify our theoretical findings with a broad range of experiments\, including with several popular deep neural net architectures and several standard post-hoc calibration methods. Our algorithm is a general-purpose tool\, which—combined with classical tests for calibration of discrete-valued predictors—can be used to test the calibration of virtually any classification method. \n— \nBio: Edgar Dobriban is an assistant professor of statistics & computer science at the University of Pennsylvania. He obtained a PhD in statistics from Stanford University in 2017\, and a BA in Mathematics from Princeton University in 2012. His research interests include the statistical analysis of large datasets\, and the theoretical analysis of machine learning. He has received a Theodore W. Anderson award for the best PhD in theoretical statistics from Stanford University\, and an NSF CAREER award. More information is available at his website \nhttps://statistics.wharton.upenn.edu/profile/dobriban/. \n— \nA full schedule for Spring 2022 Stochastics and Statistics Seminars can be found here:https://stat.mit.edu/seminars/upcoming/
URL:https://idss.mit.edu/calendar/optimal-testing-for-calibration-of-predictive-models/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220218T110000
DTEND;TZID=America/New_York:20220218T120000
DTSTAMP:20221206T054213
CREATED:20220124T203258Z
LAST-MODIFIED:20220214T212225Z
UID:15679-1645182000-1645185600@idss.mit.edu
SUMMARY:On the power of Lenstra-Lenstra-Lovasz in noiseless inference
DESCRIPTION:Abstract: In this talk\, we are going to discuss a new polynomial-time algorithmic framework for inference problems\, based on the celebrated Lenstra-Lenstra-Lovasz lattice basis reduction algorithm. Potentially surprisingly\, this algorithmic framework is able to successfully bypass multiple suggested notions of “computational hardness for inference” for various noiseless settings. Such settings include 1) sparse regression\, where there is Overlap Gap Property and low-degree methods fail\, 2) phase retrieval where Approximate Message Passing fails and 3) Gaussian clustering where the SoS hierarchy fails. In particular\, our results\, similar to the folklore but specific Gaussian elimination application in random XORSAT\, highlight the crucial but subtle role of noise in the onset of statistical-to-computational gaps. \nThis is based on joint works with David Gamarnik\, Eren Kizildag\, Min Jae Song\, Joan Bruna and Alex Wein. \n– \nBio: Ilias Zadik is a postdoctoral researcher at the Mathematics Department of MIT\, working with Professor Elchanan Mossel and Professor Nike Sun. Previously\, he spent two years as a postdoctoral fellow at the Center of Data Science of NYU\, and before that he received his PhD in 2019 from the Operations Research Center of MIT under the supervision of Professor David Gamarnik. His research lies broadly on the interface of high-dimensional statistics\, the theory of machine learning and applied probability. He is especially interested in understanding the statistical and computational trade-offs appearing in high dimensional inference.
URL:https://idss.mit.edu/calendar/zadik/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220204T110000
DTEND;TZID=America/New_York:20220204T120000
DTSTAMP:20221206T054213
CREATED:20220125T135627Z
LAST-MODIFIED:20220202T211029Z
UID:15702-1643972400-1643976000@idss.mit.edu
SUMMARY:The Brownian transport map
DESCRIPTION:Abstract: \nThe existence of a transport map from the standard Gaussian leads to succinctrepresentations for\, potentially complicated\, measures. Inspired by result from optimal transport\, we introduce the Brownian transport map that pushes forward the Wiener measure to a target measure in a finite-dimensional Euclidean space. \nUsing tools from Ito’s and Malliavin’s calculus\, we show that the map is Lipschitz in several cases of interest. Specifically\, our results apply when the target measure satisfies one of the following: \n– More log-concave than the Gaussian\, recovering a result of Caffarelli. \n– Bounded convex support with a semi log-concave density\, providing an affirmative answer to a question first posed for the Brenier map. \n– A mixture of Gaussians\, explaining recent results about dimension-free functional inequalities for such measures. \n– log-concave and isotropic. In this case\, we establish a direct connection between the Poincare constant and the (averaged) Lipschitz constant of the Brownian transport map. Since the Poincare constant is the object of the famous KLS conjecture\, we essentially show that the conjecture is equivalent to the existence of a suitable transportation map. \nJoint work with Yair Shenfeld \nBio: \nDan Mikulincer is an instructor (postdoc) at MIT Mathematics. Previously\, he finished his Ph.D. at the Weizmann Institute\, Faculty of Mathematics\, where he was advised by Ronen Eldan. He completed his B.Sc. in Mathematics and Computer Science at Ben-Gurion University (BGU)\, where he also studied Cognitive Neuroscience. He spent the summer of 2019 at Microsoft Research AI\, hosted by Sébastien Bubeck\, and is also an Azrieli fellow. His research interests broadly lie at the union of high-dimensional geometry\, probability\, statistics\, information theory\, and their relation to data science and learning theory. He is particularly interested in normal approximations and dimension-free phenomena.
URL:https://idss.mit.edu/calendar/tbd-25/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211203T110000
DTEND;TZID=America/New_York:20211203T120000
DTSTAMP:20221206T054213
CREATED:20210818T194203Z
LAST-MODIFIED:20211119T135518Z
UID:14844-1638529200-1638532800@idss.mit.edu
SUMMARY:The Geometry of Particle Collisions: Hidden in Plain Sight
DESCRIPTION:Abstract:\nSince the 1960s\, particle physicists have developed a variety of data analysis strategies for the goal of comparing experimental measurements to theoretical predictions. Despite their numerous successes\, these techniques can seem esoteric and ad hoc\, even to practitioners in the field. In this talk\, I explain how many particle physics analysis tools have a natural geometric interpretation in an emergent “space” of collider events induced by the Wasserstein metric. This in turn suggests new analysis strategies to interpret generic point cloud data sets.\n\n\nBio:\nJesse Thaler is a theoretical particle physicist who fuses techniques from quantum field theory and machine learning to address outstanding questions in fundamental physics. His current research is focused on maximizing the discovery potential of the Large Hadron Collider through new theoretical frameworks and novel data analysis techniques. Prof. Thaler joined the MIT Physics Department in 2010\, and is currently a Professor in the Center for Theoretical Physics. He was a Miller Fellow at U.C. Berkeley from 2006 to 2009\, and he received his Ph.D. in Physics from Harvard. He was awarded a Presidential Early Career Award for Scientists and Engineers in 2012 and a Sloan Research Fellowship in 2013. In 2020\, Prof. Thaler became the inaugural Director of the NSF Institute for Artificial Intelligence and Fundamental Interactions (IAIFI).
URL:https://stat.mit.edu/calendar/thaler/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211119T110000
DTEND;TZID=America/New_York:20211119T120000
DTSTAMP:20221206T054213
CREATED:20210818T192910Z
LAST-MODIFIED:20211101T143329Z
UID:14842-1637319600-1637323200@idss.mit.edu
SUMMARY:Precise high-dimensional asymptotics for AdaBoost via max-margins & min-norm interpolants
DESCRIPTION:Abstract: This talk will introduce a precise high-dimensional asymptotic theory for AdaBoost on separable data\, taking both statistical and computational perspectives. We will consider the common modern setting where the number of features p and the sample size n are both large and comparable\, and in particular\, look at scenarios where the data is asymptotically separable. Under a class of statistical models\, we will provide an (asymptotically) exact analysis of the max-min-L1-margin and the min-L1-norm interpolant. In turn\, this will characterize the generalization error of AdaBoost\, when the algorithm interpolates the training data and maximizes an empirical L1 margin. On the computational front\, we will provide a sharp analysis of the stopping time when boosting approximately maximizes the empirical L1 margin. Our theory provides several insights into properties of AdaBoost; for instance\, the larger the dimensionality ratio p/n\, the faster the optimization reaches interpolation. Our statistical and computational arguments can handle (1) finite-rank spiked covariance models for the feature distribution and (2) variants of AdaBoost corresponding to general Lq-geometry\, for q in [1\,2]. This is based on joint work with Tengyuan Liang. \n—————– \nBio: \nPragya Sur is an Assistant Professor in the Statistics Department at Harvard University. Her research broadly spans high-dimensional statistics\, statistical machine learning\, robust inference and prediction for multi-study/multi-environment heterogeneous data. She is simultaneously interested in applications of large scale statistical methods to computational neuroscience and genetics. Her research is currently supported by a William F. Milton Fund Award and an NSF DMS award. Previously\, she was a postdoctoral fellow at the Center for Research on Computation and Society\, Harvard John A. Paulson School of Engineering and Applied Sciences. She received a Ph.D. in Statistics from Stanford University in 2019\, where she received the Theodore W. Anderson Theory of Statistics Dissertation Award and a Ric Weiland Graduate Fellowship in the Humanities and Sciences. \n
URL:https://stat.mit.edu/calendar/sur/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211112T110000
DTEND;TZID=America/New_York:20211112T120000
DTSTAMP:20221206T054213
CREATED:20210818T192354Z
LAST-MODIFIED:20211021T182021Z
UID:14840-1636714800-1636718400@idss.mit.edu
SUMMARY:Characterizing the Type 1-Type 2 Error Trade-off for SLOPE
DESCRIPTION:Abstract: Sorted L1 regularization has been incorporated into many methods for solving high-dimensional statistical estimation problems\, including the SLOPE estimator in linear regression. In this talk\, we study how this relatively new regularization technique improves variable selection by characterizing the optimal SLOPE trade-off between the false discovery proportion (FDP) and true positive proportion (TPP) or\, equivalently\, between measures of type I and type II error. Additionally\, we show that on any problem instance\, SLOPE with a certain regularization sequence outperforms the Lasso\, in the sense of having a smaller FDP\, larger TPP and smaller L2 estimation risk simultaneously. Our proofs are based on a novel technique that reduces a variational calculus problem to a class of infinite-dimensional convex optimization problems and a very recent result from approximate message passing (AMP) theory. With SLOPE being a particular example\, we discuss these results in the context of a general program for systematically deriving exact expressions for the asymptotic risk of estimators that are solutions to a broad class of convex optimization problems via AMP. Collaborators on this work include Zhiqi Bu\, Jason Klusowski\, and Weijie Su (https://arxiv.org/abs/1907.07502 and https://arxiv.org/abs/2105.13302) and Oliver Feng\, Ramji Venkataramanan\, and Richard Samworth (https://arxiv.org/abs/2105.02180). \n– \nBio: Cynthia Rush is the Howard Levene Assistant Professor of Statistics in the Department of Statistics at Columbia University. In May\, 2016\, she received a Ph.D. in Statistics from Yale University under the supervision of Andrew Barron and she completed her undergraduate coursework at the University of North Carolina at Chapel Hill where she obtained a B.S. in Mathematics. She received an NSF CRIII award in 2019\, was an NTT Research Fellow at the Simons Institute for the Theory of Computing for the program on Probability\, Computation\, and Geometry in High Dimensions in Fall 2020\, and is currently a Google Research Fellow at the Simons Institute for the Theory of Computing for the program on Computational Complexity of Statistical Inference.
URL:https://stat.mit.edu/calendar/rush/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211105T110000
DTEND;TZID=America/New_York:20211105T120000
DTSTAMP:20221206T054213
CREATED:20210818T192103Z
LAST-MODIFIED:20211102T175713Z
UID:14838-1636110000-1636113600@idss.mit.edu
SUMMARY:Asymptotics of learning on dependent and structured random objects
DESCRIPTION:Abstract: Classical statistical inference relies on numerous tools from probability theory to study the properties of estimators. However\, these same tools are often inadequate to study modern machine problems that frequently involve structured data (e.g networks) or complicated dependence structures (e.g dependent random matrices). In this talk\, we extend universal limit theorems beyond the classical setting. Firstly\, we consider distributionally \structured” and dependent random object i.e random objects whose distribution are invariant under the action of an amenable group. We show\, under mild moment and mixing conditions\, a series of universal second and third order limit theorems: central-limit theorems\, concentration inequalities\, Wigner semi-circular law and Berry-Esseen bounds. The utility of these will be illustrated by a series of examples in machine learning\, network and information theory. Secondly\nby building on these results\, we establish the asymptotic distribution of the cross-\nvalidated risk with the number of folds allowed to grow at an arbitrary rate. Using this\, we study the statistical speed-up of cross validation compared to a train-test split procedure\, which reveals surprising results even when used on simple estimators. \nBio: Morgane Austern is an assistant professor at Harvard University in the statistics department. Her research focuses on problems in probability and statistics that are motivated by machine learning. She graduated with a PhD in statistics from Columbia University in 2019 where she worked in collaboration with Peter Orbanz and Arian Maleki on limit theorems for dependent and structured data. Previously\, she was also a postdoctoral researcher at Microsoft Research New England.
URL:https://stat.mit.edu/calendar/austern/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211029T110000
DTEND;TZID=America/New_York:20211029T120000
DTSTAMP:20221206T054213
CREATED:20210818T191208Z
LAST-MODIFIED:20211020T145253Z
UID:14836-1635505200-1635508800@idss.mit.edu
SUMMARY:Revealing the simplicity of high-dimensional objects via pathwise analysis
DESCRIPTION:Abstract: One of the main reasons behind the success of high-dimensional statistics and modern machine learning in taming the curse of dimensionality is that many classes of high-dimensional distributions are surprisingly well-behaved and\, when viewed correctly\, exhibit a simple structure. This emergent simplicity is in the center of the theory of “high-dimensional phenomena”\, and is manifested in principles such as “Gaussian-like behavior” (objects of interest often inherit the properties of the Gaussian measure)\, “dimension-free behavior” (expressed in inequalities which do not depend on the dimension) and “mean-field behavior” (where the behavior of a system having many degrees of freedom can be compared to a “limit object” having a small number thereof). \nIn this talk\, we present a new analytic approach that helps reveal phenomenona of this nature. The approach is based on pathwise analysis: We construct a sampling procedure associated with the high-dimensional object\, which uses the randomness coming from a Brownian motion. This gives rise to a stochastic process which allows us to make the object tractable by the analysis of the process\, via Ito calculus (the theory of diffusing particles) and relate quantities of interest of the object with the behavior of the process\, for example\, through differentiation with respect to time. \nI will try to explain how this approach works and will briefly discuss several results\, of relevance to high dimensional statistics and machine learning\, that stem from it. These results include concentration inequalities\, central limit theorems and “mean-field” structure theorems. \n\n\n–\n\nBio: Ronen Eldan works at the Weizmann Institute of Science\, and spends the current year at the Institute for Advanced Studies in Princeton. He studies phenomena that arise in high-dimensional settings in probability\, analysis\, mathematical physics and combinatorics\, as well as the application of these phenomena to high dimensional statistics\, machine learning and optimization and theory of computer science. One of his main projects in recent years has been to develop methods which help understand the behavior of high dimensional objects by establishing new connections with the field of stochastic calculus.
URL:https://stat.mit.edu/calendar/eldan/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211022T110000
DTEND;TZID=America/New_York:20211022T120000
DTSTAMP:20221206T054213
CREATED:20210818T190944Z
LAST-MODIFIED:20211018T122124Z
UID:14834-1634900400-1634904000@idss.mit.edu
SUMMARY:Instance Dependent PAC Bounds for Bandits and Reinforcement Learning
DESCRIPTION:Abstract: The sample complexity of an interactive learning problem\, such as multi-armed bandits or reinforcement learning\, is the number of interactions with nature required to output an answer (e.g.\, a recommended arm or policy) that is approximately close to optimal with high probability. While minimax guarantees can be useful rules of thumb to gauge the difficulty of a problem class\, algorithms optimized for this worst-case metric often fail to adapt to “easy” instances where fewer samples suffice. In this talk\, I will highlight some my group’s work on algorithms that obtain optimal\, finite time\, instance dependent sample complexities that scale with the true difficult of the particular instance\, versus just the worst-case. In particular\, I will describe a unifying experimental design based approach used to obtain such algorithms for best-arm identification for linear bandits\, contextual bandits with arbitrary policy classes\, and smooth losses for linear dynamical systems.\n–\nBio: Kevin Jamieson is an Assistant Professor in the Paul G. Allen School of Computer Science & Engineering at the University of Washington and is the Guestrin Endowed Professor in Artificial Intelligence and Machine Learning. He received his B.S. in 2009 from the University of Washington\, his M.S. in 2010 from Columbia University\, and his Ph.D. in 2015 from the University of Wisconsin – Madison under the advisement of Robert Nowak\, all in electrical engineering. He returned to the University of Washington as faculty in 2017 after a postdoc with Benjamin Recht at the University of California\, Berkeley. Jamieson’s research explores how to leverage already-collected data to inform what future measurements to make next\, in a closed loop. His work ranges from theory to practical algorithms with guarantees to open-source machine learning systems and has been adopted in a range of applications\, including measuring human perception in psychology studies\, adaptive A/B/n testing in dynamic web-environments\, numerical optimization\, and efficient tuning of hyperparameters for deep neural networks.
URL:https://stat.mit.edu/calendar/jamieson/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211015T110000
DTEND;TZID=America/New_York:20211015T120000
DTSTAMP:20221206T054213
CREATED:20210818T185538Z
LAST-MODIFIED:20211007T193028Z
UID:14832-1634295600-1634299200@idss.mit.edu
SUMMARY:Breaking the Sample Size Barrier in Reinforcement Learning
DESCRIPTION:Abstract:\nReinforcement learning (RL)\, which is frequently modeled as sequential learning and decision making in the face of uncertainty\, is garnering growing interest in recent years due to its remarkable success in practice. In contemporary RL applications\, it is increasingly more common to encounter environments with prohibitively large state and action space\, thus imposing stringent requirements on the sample efficiency of the RL algorithms in use. Despite the empirical success\, however\, the theoretical underpinnings for many popular RL algorithms remain highly inadequate even for the tabular setting.\nIn this talk\, we present two vignettes regarding the sample efficiency of RL algorithms. The first vignette demonstrates that a perturbed model-based RL approach is minimax optimal under a generative model\, without suffering from a sample size barrier that was present in all past work. In the second vignette\, we pin down the sample complexity of Q-learning on Markovian samples\, which substantially improves upon prior results by a factor at least as large as the dimension of the state-action space. These results cover two distinctive RL paradigms and might shed light on the efficacy of these algorithms in more complicated scenarios. \nBio:\nYuting Wei is currently an assistant professor in the Statistics and Data Science Department at the Wharton School\, University of Pennsylvania. Prior to that\, Yuting spent two years at Carnegie Mellon University as an assistant professor of statistics\, and one year at Stanford University as a Stein Fellow. She received her Ph.D. in statistics at University of California\, Berkeley\, working with Martin Wainwright and Aditya Guntuboyina. She was the recipient of the 2018 Erich L. Lehmann Citation from the Berkeley statistics department for her Ph.D. dissertation in theoretical statistics. Her research interests include high-dimensional and non-parametric statistics\, statistical machine learning\, and reinforcement learning.
URL:https://stat.mit.edu/calendar/wei/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211008T110000
DTEND;TZID=America/New_York:20211008T120000
DTSTAMP:20221206T054213
CREATED:20210818T185330Z
LAST-MODIFIED:20210924T191943Z
UID:14830-1633690800-1633694400@idss.mit.edu
SUMMARY:Recent results in planted assignment problems
DESCRIPTION:Abstract: Motivated by applications such as particle tracking\, network de-anonymization\, and computer vision\, a recent thread of research is devoted to statistical models of assignment problems\, in which the data are random weight graphs correlated with the latent permutation. In contrast to problems such as planted clique or stochastic block model\, the major difference here is the lack of low-rank structures\, which brings forth new challenges in both statistical analysis and algorithm design.\n\n \nIn the first half of the talk\, we discuss the linear assignment problem\, where the goal is to reconstruct a perfect matching planted in a randomly weighted bipartite graph\, whose planted and unplanted edge weights are independently drawn from two different distributions. We determine the sharp threshold at which the optimal reconstruction error (fraction of misclassified edges) exhibits a phase transition from imperfect to perfect. Furthermore\, for exponential weight distributions\, this phase transition is shown to be of infinite order\, confirming the conjecture of Semerjian\, Sicuro\, and Zdeborova. The negative result is shown by proving that\, below the threshold\, the posterior distribution is concentrated away from the hidden matching by constructing exponentially many long augmenting cycles. \nIn the second half of the talk\, we discuss the quadratic assignment problem (graph matching)\, where the goal is to recover the hidden vertex correspondence between two edge-correlated Erdos-Renyi graphs. We prove that there exists a sharp threshold\, above which one can correctly match all but a vanishing fraction of the vertices and below which matching any positive fraction is impossible\, a phenomenon known as the “all-or-nothing” phase transition. The proof builds upon a tight characterization of the mutual information via the truncated second-moment method and an appropriate “area theorem”. Achieving these thresholds with efficient algorithms remains open. \nThis talk is based on joint work with Jian Ding\, Jiaming Xu\, Dana Yang and Sophie Yu. Preprints available at:https://arxiv.org/abs/2103.09383\, https://arxiv.org/abs/2008.10097\, https://arxiv.org/abs/2102.00082. \n– \n\nBio: Yihong Wu is an associate professor in the Department of Statistics and Data Science at Yale University. He received his B.E. degree from Tsinghua University in 2006 and Ph.D. from Princeton University in 2011. He is a recipient of the NSF CAREER award in 2017 and Sloan fellowship in 2018. He is broadly interested in the theoretical and algorithmic aspects of high-dimensional statistics\, information theory\, and optimization.
URL:https://stat.mit.edu/calendar/wu/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20211001T110000
DTEND;TZID=America/New_York:20211001T120000
DTSTAMP:20221206T054213
CREATED:20210818T184600Z
LAST-MODIFIED:20210922T121320Z
UID:14828-1633086000-1633089600@idss.mit.edu
SUMMARY:Causal Matrix Completion
DESCRIPTION:Matrix completion is the study of recovering an underlying matrix from a sparse subset of noisy observations. Traditionally\, it is assumed that the entries of the matrix are “missing completely atrandom” (MCAR)\, i.e.\, each entry is revealed at random\, independent of everything else\, with uniform probability. This is likely unrealistic due to the presence of “latent confounders”\, i.e.\, unobserved factors that determine both the entries of the underlying matrix and the missingness pattern in the observed matrix. \n\nIn general\, these confounders yield “missing not at random” (MNAR) data\, which can severely impact any inference procedure that does not correct for this bias. We develop a formal causal model for matrix completion with MNAR data through the language of potential outcomes\, and provide identification arguments for causal estimand of interest. We design a procedure\, which we call “synthetic nearest neighbors” (SNN)\, to estimate these causal estimands. We prove finite-sample consistency and asymptotic normality of our estimator. Our analysis also leads to new theoretical results for the matrix completion literature. In particular\, we establish entry-wise\, i.e.\, max-norm\, finite-sample consistency and asymptotic normality results for matrix completion with MNAR data. As a special case\, this also provides entry-wise bounds for matrix completion with MCAR data. Across simulated and real data\, we demonstrate the efficacy of our proposed estimator.\n\n\n\nThis is based on joint works with Anish Agarwal (MIT)\, Munzer Dahleh (MIT) and Dennis Shen (UC Berkeley).\n\n\nBio: Devavrat Shah is the Andrew (1956) and Erna Viterbi Professor with the department of electrical engineering and computer science\, MIT. He is a member of LIDS and the ORC\, and the Faculty Director of the MicroMasters in Statistics and Data Science program at IDSS. His research focus is on theory of large complex networks\, which includes network algorithms\, stochastic networks\, network information theory and large-scale statistical inference.
URL:https://stat.mit.edu/calendar/shah/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210924T110000
DTEND;TZID=America/New_York:20210924T120000
DTSTAMP:20221206T054213
CREATED:20210818T182019Z
LAST-MODIFIED:20210920T132357Z
UID:14826-1632481200-1632484800@idss.mit.edu
SUMMARY:Representation and generalization
DESCRIPTION:Abstract: Self-supervised learning is an increasingly popular approach for learning representations of data that can be used for downstream representation tasks. A practical advantage of self-supervised learning is that it can be used on unlabeled data. However\, even when labels are available\, self-supervised learning can be competitive with the more “traditional” approach of supervised learning. \n \nIn this talk we consider “self supervised + simple classifier (SSS)” algorithms\, which are obtained by first learning a self-supervised classifier on data\, and then reusing the same data and its labels to fit a simple (e.g.\, linear) classifier on these data. We show that: \n \n1) Unlike traditional end-to-end supervised learning algorithms\, SSS algorithm have small generalization gaps in practice\, even when the final classifier is highly over-parameterized. \n \n2) Under natural assumptions we can prove that the generalization gap will tend to zero if the number of samples is sufficiently larger than the complexity of the simple classifier\, independently of the complexity of the self-supervised model. We show that the bound proven yields non-vacuous guarantees for many popular representation-learning based classifiers on CIFAR-10 and ImageNet\, including SimCLR\, AMDIM and BigBiGAN. \n \n3) We give evidence that self-supervised and fully supervised models learn similar representations\, by showing that the self-supervised layers can be “stitched” to the bottom of a fully-supervised model\, and vice versa\, without a significant loss of performance. \n \nBased on joint works with Bansal and Kaplun ( https://arxiv.org/abs/2010.08508 )\, and Bansal and Nakkiran ( https://arxiv.org/abs/2106.07682 ). \n \nBio: Boaz Barak is the Gordon McKay professor of Computer Science at Harvard University’s John A. Paulson school of Engineering and Applied Sciences. His research interests include all areas of theoretical computer science and in particular cryptography and computational complexity. Previously\, he was a principal researcher at Microsoft Research New England\, and before that an associate professor (with tenure) at Princeton University’s computer science department. Barak has won the ACM dissertation award\, the Packard and Sloan fellowships\, and was also selected for Foreign Policy magazine’s list of 100 leading global thinkers for 2014 and chosen as a Simons investigator in 2017 .
URL:https://stat.mit.edu/calendar/barak/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210917T110000
DTEND;TZID=America/New_York:20210917T120000
DTSTAMP:20221206T054213
CREATED:20210818T175733Z
LAST-MODIFIED:20210913T190400Z
UID:14822-1631876400-1631880000@idss.mit.edu
SUMMARY:Interpolation and learning with scale dependent kernels
DESCRIPTION:Speaker: Lorenzo Rosasco (MIT/Universita’ di Genova) \nTitle: Interpolation and learning with scale dependent kernels \nAbstract: We study the learning properties of nonparametric ridge-less least squares. In particular\, we consider the common case of estimators defined by scale dependent (Matern) kernels\, and focus on the role scale and smoothness. These estimators interpolate the data and the scale can be shown to control their stability to noise and sampling. Larger scales\, corresponding to smoother functions\, improve stability with respect to sampling. However\, smaller scales\, corresponding to more complex functions\, improve stability to noise. We will discuss to which extent these results can explain the learning curves observed for large overparameterized models. Our analysis combines\, probabilistic results with analytic techniques from interpolation theory. \nBio: Lorenzo Rosasco is an assistant professor at the University of Genova\, Italy. He is also affiliated with the Massachusetts Institute of Technology(MIT)\, where is a visiting professor\, and with the Istituto Italiano di Tecnologia (IIT)\, where he is an external collaborator. He is leading the efforts to establish the Laboratory for Computational and Statistical Learning (LCSL)\, born from a collaborative agreement between IIT and MIT. He received his PhD from the University of Genova in 2006. Dr. Rosasco has developed and analyzed methods to learn from small as well as large samples of high dimensional data\, using analytical and probabilistic tools\, within a multidisciplinary approach drawing concepts and techniques primarily from computer science but also from statistics\, engineering and applied mathematics. \n
URL:https://stat.mit.edu/calendar/rosasco/
LOCATION:E18-304\, United States
CATEGORIES:Stochastics and Statistics Seminar Series
END:VEVENT
END:VCALENDAR