# Michael Kearns

Michael Kearns is an American computer scientist and professor at the University of Pennsylvania, specializing in algorithmic game theory, machine learning, and fairness in artificial intelligence.

Michael Kearns is an American computer scientist and professor at the University of Pennsylvania, where he holds appointments in the Computer and Information Science department and the Wharton School. He is known for his contributions to algorithmic game theory, [machine learning](https://www.wikiprompt.org/wiki/machine-learning), and the study of fairness and transparency in [artificial intelligence](https://www.wikiprompt.org/wiki/artificial-intelligence) systems. Kearns has also served as a researcher at [Google DeepMind](https://www.wikiprompt.org/wiki/google-deepmind) and has been a prominent voice in discussions on the societal impacts of AI.

Kearns received his PhD in computer science from Harvard University in 1989, under the supervision of Leslie Valiant. His early work focused on computational learning theory, including the development of efficient algorithms for learning Boolean formulas and the analysis of the PAC (probably approximately correct) learning model. He later expanded his research to include algorithmic game theory, where he studied the complexity of computing Nash equilibria and the design of mechanisms for strategic settings.

## Academic Career

Kearns began his academic career as a professor at [Carnegie Mellon University](https://www.wikiprompt.org/wiki/carnegie-mellon-university) before moving to the University of Pennsylvania in 2002. At Penn, he co-founded the Networked Systems and Security Lab and has been a key figure in the interdisciplinary Warren Center for Networked Data. He has also held visiting positions at [MIT CSAIL](https://www.wikiprompt.org/wiki/mit-csail) and [Stanford AI Lab](https://www.wikiprompt.org/wiki/stanford-ai-lab). His teaching has covered topics such as machine learning, algorithmic game theory, and the ethics of AI.

## Research Contributions

Kearns has made significant contributions to several areas. In computational learning theory, he introduced the notion of "statistical queries" and proved limitations on learning from such queries. In algorithmic game theory, he co-authored the influential book "The Complexity of Nash Equilibria" and showed that finding a Nash equilibrium is PPAD-complete, a result that has shaped the field. More recently, his work has focused on fairness in machine learning, particularly the development of algorithms that ensure non-discriminatory outcomes across different demographic groups. He has also explored the use of [neural networks](https://www.wikiprompt.org/wiki/neural-network) and [deep learning](https://www.wikiprompt.org/wiki/deep-learning) in financial and social contexts.

## Industry and Policy Work

Beyond academia, Kearns has worked as a researcher at [Google DeepMind](https://www.wikiprompt.org/wiki/google-deepmind), where he contributed to projects on algorithmic fairness and interpretability. He has also served as an advisor to various tech companies and government agencies, including the National Science Foundation and the White House Office of Science and Technology Policy. He has testified before Congress on the ethical implications of AI and has been a frequent commentator in the media on topics such as algorithmic bias and the regulation of [large language models](https://www.wikiprompt.org/wiki/large-language-model).

## Awards and Recognition

Kearns has received numerous awards for his research, including the Gödel Prize in 2012 for his work on the complexity of Nash equilibria, and the Presidential Young Investigator Award in 1991. He is a fellow of the Association for Computing Machinery and the American Association for the Advancement of Science. In 2023, he was elected to the National Academy of Engineering for his contributions to algorithmic game theory and machine learning.

## Selected Publications

Kearns has authored over 100 papers and several books. Notable publications include "The Computational Complexity of Nash Equilibria" (with Christos Papadimitriou and others), "An Introduction to Computational Learning Theory" (with Umesh Vazirani), and "Fairness in Machine Learning: A Survey" (with Aaron Roth). His work has been cited tens of thousands of times and has influenced both theoretical and applied research in AI.

## Personal Life

Kearns is married and has two children. He is an avid runner and has completed several marathons. He is also a supporter of arts education and has served on the board of a local theater company.

---
Source: https://www.wikiprompt.org/wiki/michael-kearns
License: CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)
Last updated: 2026-09-05T13:27:55.142699+00:00