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


Spring 2016: CMPSCI 690-OP: Optimization for Computer Science


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). The home page for the Autonomous Learning Laboratory (ALL) describes in more detail current research projects in ML, AI, and applications that I am involved in. ALL students are working on a range of exciting projects in machine learning, from new methods for unsupervised learning, reinforcement learning, and transfer learning, to basic foundational work on optimization, and a variety of interesting applications, such as astronomy.

To showcase one project, 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.