OTHER CALENDARSABOUT THE CALENDARMORE RESOURCES 
Seminar 217, Risk Management: Robust Learning: Information Theory and AlgorithmsSeminar: Risk Seminar  October 9  11 a.m.12:30 p.m.  1011 Evans Hall Speaker: Jacob Steinhardt, Stanford Consortium for Data Analytics in Risk This talk will provide an overview of recent results in highdimensional robust estimation. The key question is the following: given a dataset, some fraction of which consists of arbitrary outliers, what can be learned about the nonoutlying points? This is a classical question going back at least to Tukey (1960). However, this question has recently received renewed interest for a combination of reasons. First, many of the older results do not give meaningful error bounds in high dimensions (for instance, the error often includes an implicit sqrt(d)factor in d dimensions). Second, recent connections have been established between robust estimation and other problems such as clustering and learning of stochastic block models. Currently, the best known results for clustering mixtures of Gaussians are via these robust estimation techniques. Finally, highdimensional biological datasets with structured outliers such as batch effects, together with security concerns for machine learning systems, motivate the study of robustness to worstcase outliers from an applied direction. 

Copyright © 2018 UC Regents
