Past Events
Events List Navigation
Hierarchical Bayesian Network Model for Probabilistic Estimation of EV Battery Life
Mehdi Jafari (LIDS)
32 – LIDS Lounge
Bayesian models are applied to probabilistic analysis of phenomena which deal with multiple external stochastic factors and unmeasurable variables. Considering the large amount of available data for the EV driving, recharging and grid services such as solar charging which contains uncertainties and measurement errors, and their hierarchical effect on the battery life, this application of Bayesian models can be useful for the aging probabilistic analysis. Causality is of utmost importance for batteries as their aging is affected by a high…
Find out more »Memory-Efficient Adaptive Optimization for Humungous-Scale Learning
Yoram Singer (Google)
32-G449 (KIva/Patel)
Adaptive gradient-based optimizers such as AdaGrad and Adam are among the methods of choice in modern machine learning. These methods maintain second-order statistics of each model parameter, thus doubling the memory footprint of the optimizer. In behemoth-size applications, this memory overhead restricts the size of the model being used as well as the number of examples in a mini-batch. We describe a novel, simple, and flexible adaptive optimization method with sublinear memory cost that retains the benefits of per-parameter adaptivity…
Find out more »Stochastics and Statistics Seminar Series
Dylan Foster (MIT)
E18-304
Logistic regression is a fundamental task in machine learning and statistics. For the simple case of linear models, Hazan et al. (2014) showed that any logistic regression algorithm that estimates model weights from samples must exhibit exponential dependence on the weight magnitude. As an alternative, we explore a counterintuitive technique called improper learning, whereby one estimates a linear model by fitting a non-linear model. Past success stories for improper learning have focused on cases where it can improve computational complexity.…
Find out more »Exponential line-crossing inequalities
Aaditya Ramdas (Carnegie Mellon University)
E18-304
Abstract: This talk will present a class of exponential bounds for the probability that a martingale sequence crosses a time-dependent linear threshold. Our key insight is that it is both natural and fruitful to formulate exponential concentration inequalities in this way. We will illustrate this point by presenting a single assumption and a single theorem that together strengthen many tail bounds for martingales, including classical inequalities (1960-80) by Bernstein, Bennett, Hoeffding, and Freedman; contemporary inequalities (1980-2000) by Shorack and Wellner,…
Find out more »Personalized Dynamic Pricing with Machine Learning: High Dimensional Covariates and Heterogeneous Elasticity
Gah-Yi Ban (London Business School)
32-155
We consider a seller who can dynamically adjust the price of a product at the individual customer level, by utilizing information about customers’ characteristics encoded as a $d$-dimensional feature vector. We assume a personalized demand model, parameters of which depend on $s$ out of the $d$ features. The seller initially does not know the relationship between the customer features and the product demand, but learns this through sales observations over a selling horizon of $T$ periods. We prove that the…
Find out more »MIT Policy Hackathon 2019
MIT Stata Center
The MIT Policy Hackathon is a 48-hour hackathon that will gather participants to work together in teams to propose creative policy solutions using a combination of robust data analytics and domain knowledge.
Find out more »SDSCon2019
MIT Media Lab Multi-Purpose room: E14-674
SDSCon 2019 is the third annual celebration of the statistics and data science community at MIT and beyond, organized by MIT’s Statistics and Data Science Center (SDSC).
Find out more »A Particulate Solution: Data Science in the Fight to Stop Air Pollution and Climate Change | IDSS Distinguished Speaker Seminar
Francesca Dominici (Harvard University)
E18-304
Abstract: What if I told you I had evidence of a serious threat to American national security – a terrorist attack in which a jumbo jet will be hijacked and crashed every 12 days. Thousands will continue to die unless we act now. This is the question before us today – but the threat doesn’t come from terrorists. The threat comes from climate change and air pollution. We have developed an artificial neural network model that uses on-the-ground air-monitoring data…
Find out more »Optimization of random polynomials on the sphere in the full-RSB regime
Eliran Subag (New York University)
E18-304
Abstract: The talk will focus on optimization on the high-dimensional sphere when the objective function is a linear combination of homogeneous polynomials with standard Gaussian coefficients. Such random processes are called spherical spin glasses in physics, and have been extensively studied since the 80s. I will describe certain geometric properties of spherical spin glasses unique to the full-RSB case, and explain how they can be used to design a polynomial time algorithm that finds points within small multiplicative error from…
Find out more »Subvector Inference in Partially Identified Models with Many Moment Inequalities
Alex Belloni (Duke University)
E18-304
Abstract: In this work we consider bootstrap-based inference methods for functions of the parameter vector in the presence of many moment inequalities where the number of moment inequalities, denoted by p, is possibly much larger than the sample size n. In particular this covers the case of subvector inference, such as the inference on a single component associated with a treatment/policy variable of interest. We consider a min-max of (centered and non-centered) Studentized statistics and study the properties of the…
Find out more »