2026 Michael Kearns: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	79	1134	1098	602	580	227	27425

Research.com Recognitions

2014 - ACM Fellow For contributions to machine learning, artificial intelligence, and algorithmic game theory and computational social science.
2012 - Fellow of the American Academy of Arts and Sciences
2003 - Fellow of the Association for the Advancement of Artificial Intelligence (AAAI) For significant contributions to computational learning theory, to reinforcement learning and stochastic planning, to dialogue agents, and to the theory of multi-agent systems.

Overview

Michael Kearns is affiliated with the University of Pennsylvania in the United States and primarily focuses on research in computer science, with a specialization in artificial intelligence. Their work spans several subfields including safety research, sociology and political science, information systems, and epidemiology.

The scientist's recent publications illustrate a diverse engagement with topics related to algorithms, privacy, and ethics. Some notable papers include:

The Ethical Algorithm: The Science of Socially Aware Algorithm Design (2021, Perspectives on Science and Christian Faith)
Mixed Differential Privacy in Computer Vision (2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition)
Confidence-ranked reconstruction of census microdata from published statistics (2023, Proceedings of the National Academy of Sciences)
Ethical algorithm design (2020, ACM SIGecom Exchanges)
An Algorithmic Framework for Bias Bounties (2022, 2022 ACM Conference on Fairness, Accountability, and Transparency)

Frequent coauthors collaborating with Michael Kearns include Aaron Roth, Zhiwei Steven Wu, Emily Diana, Ira Globus-Harris, and Alessandro Achille. The collaboration with these researchers reflects interdisciplinary efforts in areas related to their main topics of study.

Michael Kearns publishes regularly in venues such as arXiv (Cornell University), Proceedings of the National Academy of Sciences, Leibniz-Zentrum für Informatik (Schloss Dagstuhl), the ACM Conference on Fairness, Accountability, and Transparency, and Perspectives on Science and Christian Faith.

Their research focuses on key topics within computer science including:

Privacy-preserving technologies in data
Stochastic gradient optimization techniques
Ethics and social impacts of artificial intelligence
Adversarial robustness in machine learning
Machine learning and data classification
Cryptography and data security
Criminal justice and corrections analysis

Over their career, Michael Kearns has received recognition such as the ACM Fellow award in 2014 for contributions to machine learning, artificial intelligence, algorithmic game theory, and computational social science. They were also named a Fellow of the American Academy of Arts and Sciences in 2012 and a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI) in 2003, highlighting contributions to computational learning theory, reinforcement learning, stochastic planning, dialogue agents, and multi-agent systems.

Best Publications

An Introduction to Computational Learning Theory

Michael J. Kearns;Umesh V. Vazirani

2263
Citations
Cryptographic limitations on learning Boolean formulae and finite automata

Michael Kearns;Leslie Valiant

1341
Citations
Efficient noise-tolerant learning from statistical queries

Michael Kearns

1243
Citations
Near-Optimal Reinforcement Learning in Polynomial Time

Michael Kearns;Satinder Singh

1202
Citations
A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes

Michael Kearns;Yishay Mansour;Andrew Y. Ng

906
Citations
Algorithmic stability and sanity-check bounds for leave-one-out cross-validation

Michael Kearns;Dana Ron

771
Citations
Learning in the presence of malicious errors

Michael Kearns;Ming Li

771
Citations
Graphical models for game theory

Michael J. Kearns;Michael L. Littman;Satinder P. Singh

643
Citations
Efficient distribution-free learning of probabilistic concepts

Michael J. Kearns;Robert E. Schapire

585
Citations
Toward efficient agnostic learning

Michael J. Kearns;Robert E. Schapire;Linda M. Sellie

563
Citations
On the Boosting Ability of Top-Down Decision Tree Learning Algorithms

Michael Kearns;Yishay Mansour

493
Citations
On the Complexity of Teaching

S.A. Goldman;M.J. Kearns

489
Citations
Optimizing dialogue management with reinforcement learning: experiments with the NJFun system

Satinder Singh;Diane Litman;Michael Kearns;Marilyn Walker

483
Citations
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

Michael J. Kearns;Seth Neel;Aaron Roth;Zhiwei Steven Wu

465
Citations
Cryptographic Primitives Based on Hard Learning Problems

Avrim Blum;Merrick L. Furst;Michael J. Kearns;Richard J. Lipton

434
Citations
On the learnability of Boolean formulae

M. Kearns;M. Li;L. Pitt;L. Valiant

389
Citations
An Experimental Study of the Coloring Problem on Human Subject Networks

Michael Kearns;Siddharth Suri;Nick Montfort

361
Citations
Nash convergence of gradient dynamics in general-sum games

Satinder P. Singh;Michael J. Kearns;Yishay Mansour

359
Citations
Fairness in learning: classic and contextual bandits

Matthew Joseph;Michael Kearns;Jamie Morgenstern;Aaron Roth

356
Citations
Near-Optimal Reinforcement Learning in Polynominal Time

Michael J. Kearns;Satinder P. Singh

249
Citations
Proceedings of the 1997 conference on Advances in neural information processing systems 10

Michael I. Jordan;Michael J. Kearns;Sara A. Solla

91
Citations

Frequent Co-Authors

Aaron Roth University of Pennsylvania

Yishay Mansour Tel Aviv University

Satinder Singh DeepMind (United Kingdom)

Robert E. Schapire Microsoft (United States)

Sally A. Goldman Google

Umesh Vazirani University of California, Berkeley

Dana Ron Tel Aviv University

Leslie G. Valiant Harvard University

Andrew Y. Ng Stanford University

David Haussler University of California, Santa Cruz

External Links

Wikipedia of Michael Kearns Personal website of Michael Kearns Google Scholar page

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

If you’re considering studying Computer Science in the USA, there are several closely related online degrees and career pathways to explore. Interdisciplinary fields, such as environmental engineering, mechanical engineering, and physics, often intersect with computer science and open new opportunities for specialized careers.

For those focused on affordability, you may want to investigate the cheapest online environmental science degree or the cheapest mechanical engineering degree online. These programs can provide a strong foundation in science and engineering, while also integrating computer modeling and analytical skills.

Another excellent option is pursuing the cheapest online physics degree, which is valuable for students interested in software development, data analysis, or technical research roles.

If your interest leans toward big data, you can follow a data science learning path and specialize in analytics, artificial intelligence, or machine learning. Each of these degrees and pathways complements computer science and could enhance your career prospects in the tech industry.