Michael Kearns
University of Pennsylvania
|
Primary Section: 34, Computer and Information Sciences Secondary Section: 32, Applied Mathematical Sciences Membership Type:
Member
(elected 2021)
|
Biosketch
Michael Kearns is a computer scientist who has made fundamental contributions to the theory of machine learning, algorithmic game theory, computational social science, and quantitative finance. Kearns was born in California and grew up in La Jolla before attending the University of California at Berkeley, where he majored in computer science and mathematics. As a doctoral student at Harvard University, Kearns made early contributions to the theory of boosting in machine learning, and elucidated connections between machine learning and public-key cryptography. He spent the 1990s at AT&T Bell Laboratories, working on theory and applications of machine learning, including the development of the statistical query learning model. He joined the faculty of the University of Pennsylvania in 2002, and has consulted extensively in the finance and technology industries. He is co-author of “The Ethical Algorithm” (Oxford University Press, 2019). Kearns is an elected Member or Fellow of the National Academy of Sciences, the American Academy of Arts and Sciences, the Association for Computing Machinery, and the Association for the Advancement of Artificial Intelligence.
Research Interests
Michael Kearns’ research lies in the intersections of theoretical computer science, machine learning, game theory, finance, and the social sciences. His work often adopts and adapts methods from algorithm design and computational complexity to shed light on fundamental problems in machine learning, and explores new models and frameworks for learning, games, markets and strategic interaction. Kearns has worked extensively on both the computational and informational aspects of machine learning, and has conducted novel human-subject experiments on strategic interactions in social networks. Notable examples of his research include his introduction and development of the statistical query model for machine learning, which has also influenced research in differential privacy and other topics; and his work establishing connections between supervised learning models and reinforcement learning. In recent years he has primarily considered fairness, privacy and other ethical issues in machine learning and artificial intelligence.
