Sridhar Mahadevan



College of Information and Computer Science

AAAI Fellow

Co-Director, Autonomous Learning Laboratory

Editorial Board, Journal of Machine Learning Research

Research Interests

Artificial Intelligence

Machine Learning

Reinforcement Learning

Representation Discovery

Variational Inequalities


Fall 2015: CMPSCI 697L: Deep Learning

Fall 2015: Machine Learning


mahadeva AT

140 Governor’s Drive

College of Information and Computer Sciences

University of Massachusetts

Amherst MA 01003


Administrative Assistant: Susan Overstreet


My research spans across many areas of artificial intelligence (AI) and machine learning (ML). Most recently, my students and I are investigating a new framework "rethinking" AI and ML based on the concept of equilibration, which unifies a broad class of problems, including (convex) optimization, game theory, complementarity problems, networked equilibrium problems, and nonlinear equations. The approach uses the mathematical framework of variational inequalities.

For 30 years, researchers in reinforcement learning have been attempting to design a true stochastic gradient temporal difference learning method. Using the framework of variational inequalities and first-order stochastic optimization, we have recently developed a novel approach to this problem. Our approach provides the first convergence rate analysis of a linear TD type algorithm. The UAI 2015 paper on this work just received the Facebook Best (Student) Paper award.