Michael J. Kearns

Michael J. Kearns
Name	Michael J. Kearns
Nationality	American
Fields	Computer science; Machine learning; Game theory; Algorithmic fairness
Alma mater	University of Pennsylvania; Massachusetts Institute of Technology
Doctoral advisor	Dana Scott
Known for	Algorithmic fairness; Computational game theory; Machine learning theory

Michael J. Kearns is an American computer scientist known for foundational work in machine learning, algorithmic game theory, and the emerging field of algorithmic fairness. He has held faculty positions at leading institutions and contributed both theoretical results and interdisciplinary applications connecting University of Pennsylvania research traditions, Massachusetts Institute of Technology methodologies, and collaborations with industry and government laboratories. His work bridges mathematical foundations with societal concerns, engaging with topics relevant to National Science Foundation, DARPA, and technology companies.

Early life and education

Kearns received his undergraduate degree from University of Pennsylvania, where he was exposed to research environments connected to Wharton School and Penn Engineering. He completed his doctoral studies at Massachusetts Institute of Technology under the supervision of Dana Scott, linking him to intellectual lineages associated with Princeton University and Carnegie Mellon University through shared research networks. During his formative years he interacted with researchers affiliated with Bell Labs, AT&T, and the broader Silicon Valley research community, shaping his interests in learning theory, complexity, and economic models of computation.

Academic career and positions

Kearns has held faculty appointments at institutions including Harvard University and University of Pennsylvania, serving in departments connected to School of Engineering and Applied Science and collaborating with colleagues in units such as Wharton School. He has been a member of interdisciplinary centers and initiatives that involved partners like Microsoft Research, Google Research, and the IBM Watson Research Center. His roles have encompassed teaching, research leadership, and administration, engaging with graduate programs connected to Electrical Engineering and Computer Science departments and advisory boards for agencies such as National Institutes of Health and National Science Foundation panels. He has been a visiting scholar at research sites including Microsoft Research New England and policy-oriented institutions tied to Brookings Institution and RAND Corporation.

Research contributions and interests

Kearns's research encompasses theoretical machine learning, algorithmic game theory, and algorithmic fairness. He produced influential results in PAC learning connected to concepts from Valiant's framework and contributed to understanding computational complexity within the scope of NP and PSPACE-related reductions. His work on the intersection of learning and economics developed connections with John Nash-inspired equilibrium concepts and modern treatments of strategic behavior in markets related to Auction theory and Mechanism design. Kearns developed models and algorithms for privacy-preserving learning, linking to initiatives like Differential privacy and collaborations that intersect with work from Cynthia Dwork and Frank McSherry. He contributed to the formalization of algorithmic fairness metrics that interact with policy debates addressed by European Commission directives and reports from Algorithmic Accountability efforts.

Methodologically, his publications span combinatorial, probabilistic, and optimization techniques used across research groups at Stanford University, Princeton University, and MIT Computer Science and Artificial Intelligence Laboratory. He has addressed learning under strategic manipulation, connecting to literature from Joseph Bourbaki-style rigor to applied studies at Yahoo Research and Facebook AI Research. Kearns's interdisciplinary projects have tied to public-sector stakeholders such as U.S. Department of Defense initiatives and non-governmental organizations working on ethical AI including ACLU conversations and policy forums hosted by Information Technology and Innovation Foundation.

Awards and honors

Kearns has received recognition from professional societies and academic institutions, including distinctions affiliated with the Association for Computing Machinery and honors tied to research excellence often associated with awards like the NeurIPS Test of Time Award and fellowships comparable to those granted by IEEE and American Academy of Arts and Sciences. He has been invited to give plenary addresses at major conferences such as NeurIPS, ICML, and COLT, and to serve on program committees alongside laureates linked to Turing Award winners. His advisory roles have led to appointments on panels funded by National Science Foundation and consultancies with research arms of Google, Microsoft, and Amazon.

Selected publications and influence

Kearns's publications include influential papers and books that shaped contemporary conversations in theoretical and applied machine learning. His coauthored works appear in proceedings of Journal of the ACM and conferences like NeurIPS and ICML, and his monograph-level contributions have been used in curricula at Harvard and MIT. Notable collaborators and coauthors have included researchers affiliated with Princeton University, Carnegie Mellon University, Stanford University, Microsoft Research, and Google Research, reflecting a broad network across academia and industry. His work on fairness and privacy has been cited in policy documents from bodies such as the European Commission and incorporated into recommendations by organizations like IEEE and ACM.

Kearns's influence extends to mentoring students who have joined faculties at institutions including University of California, Berkeley, Cornell University, and Columbia University and to shaping research agendas in areas pursued at centers like Center for Information Technology Policy and Berkman Klein Center for Internet & Society. His ideas continue to inform debates within venues such as Brookings Institution panels and workshops organized by National Academy of Sciences.

Category:American computer scientists Category:Machine learning researchers Category:Algorithmic fairness researchers