Our Research

Control and Reinforcement Learning

Bringing tools from online learning and improper convex relaxations, our group has been working on new algorithms for control and prediction in time series that include:

Optimization for Machine Learning

Machine learning moves us from the custom-designed algorithm to generic models, such as neural networks, that are trained by optimization algorithms. Some of the most useful and efficient methods for training convex as well as non-convex methods that we have worked on include:


Online Convex Optimization

In recent years, convex optimization and the notion of regret minimization in games, have been combined and applied to machine learning in a general framework called online convex optimization. For more information see graduate text book on online convex optimization in machine learning, or survey on the convex optimization approach to regret minimization. Our research spans efficient online algorithms as well as matrix prediction algorithms, and decision making under uncertainty and continuous multi-armed bandits.