Developing foundations and principled, practical algorithms
for important modern learning paradigms. These include
interactive learning, distributed learning, transfer learning,
multi-task learning, learning representations, life-long
learning, and metalearning. My research formalizes and
explicitly addresses all constraints and important challenges of
these new settings, including statistical efficiency,
computational efficiency, noise tolerance, limited supervision
or interaction, privacy, low communication, and incentives.
Computational and data-driven approaches in game theory and
Computational, learning theoretic, and game theoretic aspects
of multi-agent systems. Analyzing the overall behavior of
complex systems in which multiple agents with limited
information are adapting their behavior based on past
experience, both in social and engineered systems contexts.
Foundations of data driven algorithm design.
Analysis of the algorithms beyond the worst case and more
generally identifying interesting and realistic models of
computation that provide a better alternative to traditional
worst-case models in a broad range of optimization problems.
For more information see the links below and my resume.
Current and Recent Selected
Program Committee Co-chair for ICML 2016 (all talks
Program Committee Co-chair for COLT
2014 (all talks available here).
Editorial Board Member: CACM
Highlights, IEEE Transactions on Pattern Analysis and
Machine Intelligence, Machine Learning Journal.