Wednesday / CS Seminar

February 14th / 12:00 PM

In Person / Mudd 3514

Speaker

Abhishek Shetty, University of California at Berkeley

Talk Title

Modeling Uncertainty for Designing Efficient Algorithms for Machine Learning

Abstract

Though modern machine learning has been highly successful, as we move towards more critical applications, many challenges towards ensuring robustness, privacy, and fairness, arise. Ad hoc and empirical approaches have often led to unintended consequences for these objectives, thus necessitating a principled approach. Traditional solutions often require redesigning entire pipelines or come with a significant loss in quality. In this talk, we will look at principles for modeling data towards can incorporating these important desiderata into existing pipelines without significant computational and statistical overhead.

We will see two vignettes of this line of research. First, the smoothed adversary model for sequential decision making, leading to statistically and computationally efficient algorithms for decision making under uncertainty. Second, we will see a nearly linear-time algorithm for distribution compression leading to improved computational efficiency in diverse downstream statistical tasks.

Biography

Abhishek Shetty is currently a PhD student in the Department of Computer Science at the University of California at Berkeley advised by Nika Haghtalab. His research focuses on designing mathematical frameworks bringing together the theory and practice of machine learning and using these to developing simple algorithms with provable guarantees on real-world data. His research has been awarded a American Statistical Association SCSG best student paper award and also the Apple AI/ML fellowship.

Research Interests/Area

Theory/Machine Learning