
Multiaccurate Proxies for Downstream Fairness
We study the problem of training a model that must obey demographic fair...
read it

Differentially Private Query Release Through Adaptive Projection
We propose, implement, and evaluate a new algorithm for releasing answer...
read it

Lexicographically Fair Learning: Algorithms and Generalization
We extend the notion of minimax fairness in supervised learning problems...
read it

Convergent Algorithms for (Relaxed) Minimax Fairness
We consider a recently introduced framework in which fairness is measure...
read it

Mathematical Foundations for Social Computing
Social computing encompasses the mechanisms through which people interac...
read it

Algorithms and Learning for Fair Portfolio Design
We consider a variation on the classical finance problem of optimal port...
read it

Differentially Private Call Auctions and Market Impact
We propose and analyze differentially private (DP) mechanisms for call a...
read it

Optimal, Truthful, and Private Securities Lending
We consider a fundamental dynamic allocation problem motivated by the pr...
read it

Network Formation under Random Attack and Probabilistic Spread
We study a network formation game where agents receive benefits by formi...
read it

Eliciting and Enforcing Subjective Individual Fairness
We revisit the notion of individual fairness first proposed by Dwork et ...
read it

Average Individual Fairness: Algorithms, Generalization and Experiments
We propose a new family of fairness definitions for classification probl...
read it

Equilibrium Characterization for Data Acquisition Games
We study a game between two firms in which each provide a service based ...
read it

Differentially Private Fair Learning
We design two learning algorithms that simultaneously promise differenti...
read it

Fair Algorithms for Learning in Allocation Problems
Settings such as lending and policing can be modeled by a centralized ag...
read it

An Empirical Study of Rich Subgroup Fairness for Machine Learning
Kearns et al. [2018] recently proposed a notion of rich subgroup fairnes...
read it

Online Learning with an Unknown Fairness Metric
We consider the problem of online learning in the linear contextual band...
read it

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
The most prevalent notions of fairness in machine learning are statistic...
read it

A Convex Framework for Fair Regression
We introduce a flexible family of fairness regularizers for (linear and ...
read it

Fairness in Criminal Justice Risk Assessments: The State of the Art
Objectives: Discussions of fairness in criminal justice risk assessments...
read it

Fairness in Learning: Classic and Contextual Bandits
We introduce the study of fairness in multiarmed bandit problems. Our f...
read it

An InformationTheoretic Analysis of Hard and Soft Assignment Methods for Clustering
Assignment methods are at the heart of many algorithms for unsupervised ...
read it

Large Deviation Methods for Approximate Probabilistic Inference
We study twolayer belief networks of binary random variables in which t...
read it

Exact Inference of Hidden Structure from Sample Data in NoisyOR Networks
In the literature on graphical models, there has been increased attentio...
read it

Fast Planning in Stochastic Games
Stochastic games generalize Markov decision processes (MDPs) to a multia...
read it

Graphical Models for Game Theory
In this work, we introduce graphical modelsfor multiplayer game theory,...
read it

Efficient Nash Computation in Large Population Games with Bounded Influence
We introduce a general representation of largepopulation games in which...
read it

Graphical Models for Bandit Problems
We introduce a rich class of graphical models for multiarmed bandit pro...
read it
Michael Kearns
is this you? claim profile
He has been the founding Director of the Penn’s Singh Network & Social Systems Engineering Program, the founding director of the Warren Center for Networking and Data Science, and also has secondary appointments to the Penn’s Wharton School and the Development Department. He is a leading researcher in theory of computer learning and the theory of algorithms and is interested in machine learning, artificial intelligence, computer finance, algorithmic commerce, computer science and social networks. He leads the consultation and research role in the team of the Artificial Intelligence Center of Excellence in Morgan Stanley.
Kearns is a native of the academic family, where David R Kearns is an Emeritus Professor at the California University, San Diego in chemistry, winner of the Guggenheim Fellowship in 1969, and his uncle Thomas R. Kearns is an Emeritus Professor at Amherst College of Philosophy and Law. His father’s grandfather Clyde W. Kearns pioneered insecticide toxicology, was a professor at the University of Illinois in the Entomology Campuses in Urbana and his mother’s grandparent Chen ShouYi was a Professor of history and literature at Pomona College. Claremont Colleges and Professor Chen are a leader in the development of Asian studies on the West Coast. Kearns got his B.S. Graduate in mathematics and computer science at the University of California, Berkeley, and Ph.D. in computer science from Harvard University in 1989. His PhD thesis was The Computational Complexity of Machine Learning, later published in 1990 by the MIT press in the ACM PhD Awards. Before joining AT&T Bell Labs in 1991, he continued his postdoctoral studies with Ronald Rivest at the MIT Computer Science Laboratory and Richard M. Karp at the International Computer Science Institute in UC Berkeley, both Turing Prize winners.
Kearns is a fulltime professor and chairman at the University of Pennsylvania, where he is appointed to the Department of Computer and Information Sciences and the Wharton School of Statistics, Operations and Information Management. He has been with AT&T Labs and Bell Labs a decade before joining Penn Faculty in 2002, including Michael L. Littman, David A. McAllester and Sutton, Head of the AI Departments and Machine Learning, Secure Systems Research and Michael Collins and Fernando Pereira. Other algorithms and theoretical computer science collaborators at AT&T Labs included Yoav Freund, Ronald Graham, Mehryar Mohri, Robert Schapire, and Peter Shor, along with Sebastian Seung, Yann LeCun, Corinna Cortes, and Vladimir Vapnik.
Kearns was nominated Fellow of the Computer Machinery Association for machinelearning contributions and a fellow of the American Academy of Arts and Sciences.
Ryan W. Porter and John Langford were his former graduates and postdoctoral visitors.
Media such as the MIT Technology Review Can a Web site help you decide to have a child have reported Kearns’ work?, Bloomberg News Schneiderman HighSpeed Trading pressures and NPR audio online education is growing up, for now it is free. It’s free.
Kearns and Umesh Vazirani published a text on computational learning theory since it was published in 1994, as a standard text.
Kearns and Valiant asked the question ‘is weak learning equivalent to strong learning?’ This is why machine learning algorithms, which were answered positively by Robert Schapire and Yoav Freund and then develop the practical AdaBoost, a adaptive boost that won the prestigious Gödel Prize.

ACM Fellow.For machine learning contributions, artificial intelligence, and algorithmic game theory, and social computing. 2012. 2012. Fellow of the American Academy of Arts and Sciences.