Michael Kearns
Generated by GPT-5-miniExpansion Funnel Raw 58 → Dedup 0 → NER 0 → Enqueued 0
| Michael Kearns | |
|---|---|
| Name | Michael Kearns |
| Birth place | United States |
| Fields | Computer science, Machine learning, Economics |
| Workplaces | University of Pennsylvania, AT&T Bell Laboratories, Amazon, GRAIL |
| Alma mater | Massachusetts Institute of Technology, Harvard University |
| Known for | Computational learning theory, Algorithmic fairness, Game theory |
Michael Kearns is an American scholar in computer science known for foundational work in machine learning, computational complexity, and the intersection of economics and algorithm design. His research spans theoretical frameworks for learning, algorithmic game theory, and principled approaches to fairness and privacy in automated systems. He has held academic positions, industrial research roles, and engaged in public debate on ethical implications of artificial intelligence.
Early life and education
Born in the United States, he pursued undergraduate and graduate study at premier institutions including Massachusetts Institute of Technology and Harvard University. At Harvard University he studied under advisors and collaborated with scholars active in computational learning theory and complexity theory, linking ideas from algorithmic game theory and statistical learning. During this period he interacted with contemporaries affiliated with AT&T Bell Laboratories, IBM Research, and other leading centers for theoretical computer science.
Academic career and research
He joined the faculty of the University of Pennsylvania where he established a research group bridging machine learning and economics. His academic appointments connected him to departments and centers engaged with artificial intelligence, including collaborations with researchers at Stanford University, Massachusetts Institute of Technology, Carnegie Mellon University, and Princeton University. He also spent time at industrial research labs such as AT&T Bell Laboratories and worked on applied projects with organizations like Amazon (company) and clinical start-ups such as GRAIL. His mentorship produced students who went on to positions at Google, Facebook, Microsoft Research, and top academic departments.
His publications appear in leading venues including NeurIPS, ICML, COLT, FOCS, and STOC, reflecting contributions that tie statistical theory to algorithmic practice. He has collaborated with scholars from economics and operations research, appearing alongside authors affiliated with Harvard University, Yale University, and University of California, Berkeley.
Contributions to theoretical computer science
His work in computational learning theory advanced formal models such as PAC learning and online learning, interacting with results from Valiant's model and developments at COLT conferences. He developed algorithmic analyses that connected to VC dimension results and complexity-theoretic perspectives that align with research from STOC and FOCS. He contributed to foundations of algorithmic fairness by formalizing notions of fairness and robustness for classifiers, drawing on interdisciplinary ideas from economics, game theory, and privacy research associated with differential privacy.
Kearns introduced and analyzed models that capture strategic behavior in learning systems, connecting to classical work in game theory and auction theory studied at Princeton University and Harvard University. His research on algorithmic mechanism design relates to the literature developed by scholars at MIT, Stanford University, and University of California, Berkeley. He also produced theoretical results on noise tolerance and adversarial examples that resonate with investigations at OpenAI, DeepMind, and academic labs addressing robustness in artificial intelligence.
In privacy and fairness, his formal frameworks influenced subsequent efforts in regulation and standards discussed by policymakers associated with European Commission and commentators from Brookings Institution and RAND Corporation. His papers propose algorithmic interventions that complement empirical methods pursued at Google Research and Microsoft Research.
Awards and honors
He has received recognition from professional societies and foundations tied to computer science and statistics, including fellowships and awards that place him among researchers honored by organizations such as the Association for Computing Machinery and the Institute of Electrical and Electronics Engineers. His work has been cited in reports by policy and research institutions including National Science Foundation-funded projects, and his lectures have been featured at major symposia hosted by NeurIPS, ICML, and AAAI.
He has served on award committees and editorial boards connected to journals and conferences like Journal of Machine Learning Research and venues organized by the Association for the Advancement of Artificial Intelligence. His collaborative grants have included multi-institutional efforts with partners at Carnegie Mellon University and University of Pennsylvania.
Personal life and activism
Beyond academia, he has been active in public discourse about the social impact of artificial intelligence, engaging with journalists at outlets that cover technology policy and ethics, and participating in forums organized by think tanks such as Brookings Institution and Harvard Kennedy School. He has testified or briefed stakeholders concerned with fairness and safety in automated decision systems, interacting with policymakers and researchers from institutions including the National Academy of Sciences and regulatory bodies in the United States and European Union.
His advocacy emphasizes responsible deployment of machine learning systems, dialogues with civil society groups, and collaborations with clinical and industry partners such as GRAIL to translate theoretical advances into practical safeguards. He resides in the United States and continues to contribute to research, teaching, and outreach connecting technical developments at institutions like University of Pennsylvania and industrial partners including Amazon (company).