Michael Kearns

Michael Kearns is an American computer scientist renowned for his foundational work in machine learning and theoretical computer science. He is a professor in the Department of Computer and Information Science at the University of Pennsylvania and holds the National Center Chair at the Penn Engineering's Warren Center for Network and Data Sciences. His research spans computational learning theory, algorithmic game theory, and the societal impacts of artificial intelligence, including algorithmic fairness and the structure of social networks.

Early life and education

Kearns completed his undergraduate studies at Harvard University, earning a Bachelor of Arts degree. He then pursued his doctoral studies at the University of California, Berkeley, under the supervision of renowned computer scientist and Turing Award recipient Manuel Blum. His doctoral dissertation contributed significantly to the emerging field of computational learning theory, establishing a strong foundation for his future research. This academic training at two of the world's leading institutions positioned him at the forefront of theoretical computer science.

Academic career

Following his Ph.D., Kearns held a postdoctoral position at Harvard University before joining the research staff at AT&T Bell Laboratories, a historic hub for innovation in information theory and computer science. He later served as a senior research scientist at the renowned NEC Labs America in Princeton, New Jersey. In 2002, he joined the faculty of the University of Pennsylvania, where he is a professor in the Department of Computer and Information Science. At Penn, he also plays a leading role in the Warren Center for Network and Data Sciences and has affiliations with the Wharton School, contributing to interdisciplinary research at the intersection of technology, economics, and sociology.

Research and contributions

Kearns' research has made seminal contributions across multiple domains within computer science. In machine learning, his early work with Leslie Valiant helped formalize the Probably Approximately Correct (PAC) learning model, a cornerstone of computational learning theory. He has conducted extensive research on the boosting algorithms, exploring their theoretical limits and applications. His later work pioneered the study of algorithmic fairness, developing frameworks to audit and mitigate bias in automated decision systems, influencing policy discussions at institutions like the Federal Trade Commission. In algorithmic game theory, he investigated computational problems in games, markets, and social networks, authoring influential texts such as *The Ethical Algorithm* with Aaron Roth. His research on the structure and dynamics of social networks has provided insights into information cascades and network science.

Awards and honors

In recognition of his contributions, Kearns has received several prestigious awards. He was the recipient of the IJCAI Computers and Thought Award, a major honor for early-career achievements in artificial intelligence. He is an elected AAAI Fellow of the Association for the Advancement of Artificial Intelligence and an ACM Fellow of the Association for Computing Machinery. His research has been supported by grants from the National Science Foundation, the Air Force Office of Scientific Research, and the Alfred P. Sloan Foundation, which awarded him a Sloan Research Fellowship. He has also served on the editorial boards of leading journals including *Journal of Machine Learning Research* and *Machine Learning*.

Selected publications

* Kearns, M., & Vazirani, U. (1994). *An Introduction to Computational Learning Theory*. MIT Press. * Kearns, M., & Mansour, Y. (1996). On the Boosting Ability of Top-Down Decision Tree Learning Algorithms. *Journal of Computer and System Sciences*. * Kearns, M., Suri, S., & Montfort, N. (2006). An Experimental Study of the Coloring Problem on Human Subject Networks. *Science*. * Kearns, M., & Roth, A. (2020). *The Ethical Algorithm: The Science of Socially Aware Algorithm Design*. Oxford University Press. * Heidari, H., Krause, A., & Kearns, M. (2019). Preventing Disparate Treatment in Sequential Decision Making. Proceedings of the *International Joint Conference on Artificial Intelligence*.

Category:American computer scientists Category:Machine learning researchers Category:Harvard University alumni Category:University of California, Berkeley alumni Category:University of Pennsylvania faculty