My research tackles fundamental questions in Machine Learning, Algorithmic Game Theory, and Algorithms. My work develops deep new connections between these areas, using ideas and insights from each of them to solve some of their central and emerging challenges in innovative ways.
Foundations for Machine Learning Machine learning studies the design of automatic methods for extracting information from data and has become a tremendously successful discipline with a wide variety of important applications in areas such as robotics, healthcare, information retrieval, and sustainability. Its past successful evolution was heavily influenced by mathematical foundations developed for several core problems including generalizing from labeled data. However, with the variety of applications of machine learning across science, engineering, and computing in the age of Big Data, re-examining the underlying foundations of the field has become imperative. A major goal of my research is to substantially advance the field of machine learning by developing foundations and algorithms for a number of important modern learning paradigms. These include interactive learning, where the algorithm and the domain expert engage in a dialogue to facilitate more accurate learning from less data compared to the classic approach of passively observing labeled data; distributed learning, where a large dataset is distributed across multiple servers and the challenge lies in learning with limited communication; and multi-task learning, where the goal is to solve multiple related learning problems from less data by taking advantage of relationship among the learning tasks. My goal is to provide new frameworks explaining the fundamental underlying principles, as well as new powerful, principled, and practical learning algorithms designed to satisfy the new types of constraints and challenges of these modern settings (including statistical efficiency, computational efficiency, noise tolerance, limited supervision or interaction, privacy, low communication, and incentives).