November 2019
Understanding machine learning with statistical physics
Lenka Zdeborová (Institute of Theoretical Physics, CNRS)
E18-304
Abstract: The affinity between statistical physics and machine learning has long history, this is reflected even in the machine learning terminology that is in part adopted from physics. Current theoretical challenges and open questions about deep learning and statistical learning call for unified account of the following three ingredients: (a) the dynamics of the learning algorithm, (b) the architecture of the neural networks, and (c) the structure of the data. Most existing theories are not taking in account all of those…
Find out more »LIDS Seminar – Sujay Sanghavi (University of Texas at Austin)
Sujay Sanghavi (University of Texas at Austin)
32-155
TBD Bio: ____________________________________ The LIDS Seminar Series features distinguished speakers who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing.
Find out more »Stability of a Fluid Model for Fair Bandwidth Sharing with General File Size Distributions
Ruth J Williams (University of California, San Diego)
E18-304
Abstract: Massoulie and Roberts introduced a stochastic model for a data communication network where file sizes are generally distributed and the network operates under a fair bandwidth sharing policy. It has been a standing problem to prove stability of this general model when the average load on the system is less than the network’s capacity. A crucial step in an approach to this problem is to prove stability of an associated measure-valued fluid model. We shall describe prior work on this question done under various strong assumptions and…
Find out more »LIDS Seminar – Rayadurgam Srikant (University of Illinois at Urbana-Champaign)
Rayadurgam Srikant (University of Illinois at Urbana-Champaign)
32-155
TBD Bio: ____________________________________ The LIDS Seminar Series features distinguished speakers who provide an overview of a research area, as well as exciting recent progress in that area. Intended for a broad audience, seminar topics span the areas of communications, computation, control, learning, networks, probability and statistics, optimization, and signal processing.
Find out more »SES PhD Admissions Webinar
Ali Jadbabaie (MIT)
Learn about admission to the Social and Engineering Systems Doctoral Program. Webinars are led by a member of the IDSS faculty who introduces the program and answers your questions. Please register in advance.
Find out more »December 2019
Automating the Digitization of Historical Data on a Large Scale
Melissa Dell (Harvard University)
E18-304
Over the past two centuries, we have transitioned from an overwhelmingly agricultural world to one with vastly different patterns of economic organization. This transition has been remarkably uneven across space and time, and has important implications for some of the most central challenges facing societies today. Deepening our understanding of the determinants of economic transformation requires data on the long-run trajectories of individuals and firms. However, these data overwhelmingly remain trapped in hard copy, with cost estimates for manual digitization…
Find out more »Inferring the Evolutionary History of Tumors
Simon Tavaré (Columbia University)
E18-304
Abstract: Bulk sequencing of tumor DNA is a popular strategy for uncovering information about the spectrum of mutations arising in the tumor, and is often supplemented by multi-region sequencing, which provides a view of tumor heterogeneity. The statistical issues arise from the fact that bulk sequencing makes the determination of sub-clonal frequencies, and other quantities of interest, difficult. In this talk I will discuss this problem, beginning with its setting in population genetics. The data provide an estimate of the…
Find out more »April 2020
SDSCon 2020
MIT Media Lab (E14-674)
SDSCon 2020 is the fourth annual celebration of the statistics and data science community at MIT and beyond, organized by MIT’s Statistics and Data Science Center (SDSC). Please see the conference website for registration information.
Find out more »