Statistics Colloquium Series

Our upcoming event for the Statistics Department Colloquium Series is scheduled for Monday, September 25 from 12:00 – 1:00pm (ET) and will be an in-person presentation Science Center Rm. 316. Lunch will be provided to guests following the talk.

This week's speaker is Ilias Diakonikolas from the Computer Science Department at University of Wisconsin-Madison. Ilias Diakonikolas is the Lubar Professor in the Department of Computer Sciences at UW Madison. He obtained a Diploma in electrical and computer engineering from the National Technical University of Athens and a Ph.D. in computer science from Columbia University where he was advised by Mihalis Yannakakis. Before moving to UW, he was an Andrew and Erna Viterbi Early Career Chair at USC and a faculty member at the University of Edinburgh. Prior to that, he was the Simons postdoctoral fellow in theoretical computer science at the University of California, Berkeley. His research is on the algorithmic foundations of massive data sets, in particular on designing efficient algorithms for fundamental problems in machine learning. He is a recipient of a Sloan Fellowship, an NSF CAREER Award, a Google Faculty Research Award, a Marie Curie Fellowship, the best paper award at NeurIPS 2019, the IBM Research Pat Goldberg Best Paper Award, and an honorable mention in the George Nicholson competition from the INFORMS society. Ilias wrote with Daniel Kane the textbook "Algorithmic High-dimensional Robust Statistics" recently published by Cambridge University Press.

Title: Algorithmic Robust Statistics

Abstract: The field of Robust Statistics studies the problem of designing estimators that perform well even when the data significantly deviates from the idealized modeling assumptions. The classical statistical theory, going back to the pioneering works by Tukey and Huber in the 1960s, characterizes the information-theoretic limits of robust estimation for a number of statistical tasks. On the other hand, until fairly recently, the computational aspects of this field were poorly understood. Specifically, no scalable robust estimation methods were known in high dimensions, even for the most basic task of mean estimation.

A recent line of work in computer science developed the first computationally efficient robust estimators in high dimensions for a range of learning tasks. This talk will provide an overview of these algorithmic developments and discuss some open problems in the area.