Seminar 217, Risk Management: Robust Learning: Information Theory and Algorithms

Risk Seminar
Oct 9, 2018 11:00am to 12:30pm
1011 Evans Hall
Happening As Scheduled
This talk will provide an overview of recent results in high-dimensional 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 non-outlying 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...
Speaker: Jacob Steinhardt, Stanford (Speaker - Featured)