Views Navigation

Event Views Navigation

Calendar of Events

S Sun

M Mon

T Tue

W Wed

T Thu

F Fri

S Sat

0 events,

0 events,

0 events,

0 events,

0 events,

1 event,

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

1 event,

Statistics and Data Science Seminar Aaditya Ramdas (Carnegie Mellon University)

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

1 event,

Statistics and Data Science Seminar Dylan Foster (MIT Institute for Foundations of Data Science)

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

1 event,

Statistics and Data Science Seminar Chao Gao (University of Chicago)

0 events,

0 events,

0 events,

0 events,

0 events,

0 events,

1 event,

Statistics and Data Science Seminar Tracy Ke (Harvard University)

0 events,

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…

Find out more »

Logistic Regression: The Importance of Being Improper

Dylan Foster (MIT Institute for Foundations of Data Science)
E18-304

Abstract: 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…

Find out more »

Robust Estimation: Optimal Rates, Computation and Adaptation

Chao Gao (University of Chicago)
E18-304

Abstract: Chao Gao will discuss the problem of statistical estimation with contaminated data. In the first part of the talk, I will discuss depth-based approaches that achieve minimax rates in various problems. In general, the minimax rate of a given problem with contamination consists of two terms: the statistical complexity without contamination, and the contamination…

Find out more »

Optimal Adaptivity of Signed-Polygon Statistics for Network Testing (Tracy Ke, Harvard University)

Tracy Ke (Harvard University)
E18-304

Abstract: Given a symmetric social network, we are interested in testing whether it has only one community or multiple communities. The desired tests should (a) accommodate severe degree heterogeneity, (b) accommodate mixed-memberships, (c) have a tractable null distribution, and (d) adapt automatically to different levels of sparsity, and achieve the optimal detection boundary. How to…

Find out more »


MIT Statistics + Data Science Center
Massachusetts Institute of Technology
77 Massachusetts Avenue
Cambridge, MA 02139-4307
617-253-1764