Vitaly Feldman is a research scientist at Google Research working on design and theoretical analysis of machine learning algorithms. His recent research interests include stability-based and information-theoretic tools for analysis of generalization, privacy-preserving learning, and adaptive data analysis.
Vitaly holds an M.Sc. degree from the Technion, Israel (2001, advised by Nader Bshouty) and a Ph.D. from Harvard (2006, advised by Leslie Valiant). Previously he was a research scientist at IBM Research Almaden (2007-2017), a postdoctoral researcher at Harvard (2006-2007) and a member of research staff at IBM Research Haifa (1997-2002, part-time). His work was recognized by the COLT Best Student Paper Award in 2005 and 2013 (student co-authored) and by the IBM Research Best Paper Award in 2014, 2015 and 2016. His recent research on foundations of adaptive data analysis has been featured in CACM (Research Highlights), Science, and the research blogs of IBM, Google, and Microsoft. He serves as a director on the steering committee of the Association for Computational Learning and was a program co-chair for COLT 2016.