Percy Liang
Associate Professor, Computer Science

Stanford University

Title: Surprises in the Quest for Robust Machine Learning

Speaker: Percy Liang, Associate Professor of Computer Science, Stanford University

Abstract:
Standard machine learning produces models that are accurate on average but degrade dramatically on when the test distribution of interest deviates from the training distribution.  We consider three settings where this happens: when test inputs are subject to adversarial attacks, when we are concerned with performance on minority subpopulations, and when the world simply changes (classic domain shift). Our aim is to produce methods that are provably robust to such deviations.  In this talk, I will provide an overview of the work my group has done on this topic over the last three years. We have found many surprises in our quest for robustness: for example, that the "more data" and "bigger models" strategy that works so well for average accuracy sometimes fails out-of-domain.  On the other hand, we have found that certain tools such as analysis of linear regression and use of unlabeled data (e.g., robust self-training) have reliably delivered promising results across a number of different settings.

Bio:
Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011). His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to communicate with through natural language. His awards include the Presidential Early Career Award for Scientists and Engineers (2019), IJCAI Computers and Thought Award (2016), an NSF CAREER Award (2016), a Sloan Research Fellowship (2015), and a Microsoft Research Faculty Fellowship (2014).