MICHAEL KEARNS Professor and National Center Chair Department of Computer and Information Science of the University of Pennsylvania Founding Director, Warren Center for Network and Data Sciences Founding Director, Penn program in Networked and Social Systems Engineering Secondary Appointments in the departments of Economics; and in Statistics and Operations, Information and Decisions in the Wharton School 509 Levine Hall, 3330 Walnut Street, Philadelphia, PA 19104-6389 Phone: (215)898-7888 Email: [email protected] Administrative Assistant: Cheryl Hickey Phone: (215)898-3538 Email: [email protected]

Most of this site is organized as a single flat html file. The links below let you navigate directly to the various subsections.

Publications   Research Group Members   Teaching and Tutorial Material   Professional Bio   Educational Background   Editorial and Professional Service   Press

RESEARCH INTERESTS

My research interests include topics in machine learning, algorithmic game theory and microeconomics, computational social science, and quantitative finance and algorithmic trading. I often examine problems in these areas using methods and models from theoretical computer science and related disciplines. While much of my work is mathematical in nature, I also often participate in empirical and experimental projects, including applications of machine learning to problems in trading and quantitative finance. For the last decade, I have occasionally been conducting human-subject experiments on strategic and economic interaction in social networks.

QUICK LINKS

Warren Center for Network and Data Sciences
Networked and Social Systems Engineering (NETS) Program
Graduate course on Computational Learning Theory, Spring 2016
Penn undergraduate course Networked Life (NETS 112), Fall 2016 and a condensed video version.
Penn-Lehman Automated Trading Project (inactive)
Tribute Day for Les Valiant, May 2009

PROFESSIONAL BIO

Current:

Since 2002 I have been a professor in the Computer and Information Science Department at the University of Pennsylvania, where I hold the National Center Chair. I have secondary appointments in the department of Economics, and in the departments of Statistics and Operations, Information and Decisions (OID) in the Wharton School. I am the Founding Director of the Warren Center for Network and Data Sciences, where my Co-Director is Rakesh Vohra. I am the faculty founder and former director of Penn Engineering's Networked and Social Systems Engineering (NETS) Program, whose current directors are Andreas Haeberlen and Aaron Roth. I am a faculty affiliate in Penn's Applied Math and Computational Science graduate program. Until July 2006 I was the co-director of Penn's interdisciplinary Institute for Research in Cognitive Science.

I am Chief Scientist of MANA Partners, a trading, technology and asset management firm based in NYC.

I often serve as an advisor to technology companies and venture capital firms. I am also involved in the seed-stage fund Founder Collective and occasionally invest in early-stage technology startups. I am a member of the Technical Advisory Board of Microsoft Research Cambridge. I occasionally serve as an expert witness or consultant on technology-related legal and regulatory cases.

I am an elected Fellow of the American Academy of Arts and Sciences, the Association for Computing Machinery, the Association for the Advancement of Artificial Intelligence, and the Society for the Advancement of Economic Theory.

The Past:

I spent the decade 1991-2001 in machine learning and AI research at AT&T Bell Labs. During my last four years there, I was the head of the AI department, which conducted a broad range of systems and foundational AI work; I also served briefly as the head of the Secure Systems Research department. The AI department boasted terrific colleagues and friends that included Charles Isbell (now at Georgia Tech), Diane Litman (now at University of Pittsburgh), Michael Littman (later at Rutgers, now at Brown), David McAllester (now at TTI-Chicago), Satinder Singh (now at University of Michigan), Peter Stone (now at University of Texas), and Rich Sutton (now at University of Alberta). Prior to my time as its head, the AI department was shaped by the efforts of a number of notable figures, including Ron Brachman (who originally founded the department; now at Yahoo! Research), Henry Kautz (who led the department before heading to the University of Washington; now at the University of Rochester), and Bart Selman (now at Cornell). Before leading the AI group, I was a member of the closely related Machine Learning department at the labs, which was headed by Fernando Pereira (later at Penn, now at Google), and included Michael Collins (later at MIT, now at Columbia), Sanjoy Dasgupta (now at UCSD), Yoav Freund (now at UCSD), Rob Schapire (now at Princeton), William Cohen (now at CMU), and Yoram Singer (later at Hebrew University, now at Google). Other friends and colleagues from Labs days include Sebastian Seung (later at MIT, now at Princeton), Lawrence Saul (later at Penn, now at UCSD), Yann LeCun (now at NYU), Roberto Pieraccini (now at SpeechCycle), Esther Levin (now at SAC Capital), Lyn Walker (now at UC Santa Cruz), Corinna Cortes (now at Google), and Vladimir Vapnik (now at Columbia and NEC). Here is a nice photo wall of former AT&T Labs theory and algorithms researchers, compiled by the great David S. Johnson.

I spent 2001 as CTO of the European venture capital firm Syntek Capital, and joined the Penn faculty in January 2002.

From early 2014 to June 2016, I led a quantitative portfolio management team with Yuriy Nevmyvaka at Engineers Gate. From June 2009 through September 2013, we were PMs in the MultiQuant division of SAC Capital in New York City. From May 2007 through April 2009, we led a quantitative trading team at Bank of America in New York City, working on both proprietary and algorithmic trading strategies within BofA's Electronic Trading Services division. From the Spring of 2002 through May 2007, I was first a consultant to, and later the head of, a quant prop trading team within the Equity Strategies group of Lehman Brothers in New York City.

I spent most of 2011 on sabbatical in Cambridge, England, where I visited the University of Cambridge Economics Department and was a visiting Fellow at Christ's College. I also spent time visiting Microsoft Research Cambridge.

I have served as an advisor to the startups Yodle, Wealthfront, Activate Networks, RootMetrics (acquired by IHS), Convertro (acquired by AOL), Invite Media (acquired by Google), SiteAdvisor (founded by Chris Dixon; acquired by McAfee), PayNearMe (formerly known as Kwedit), and Riverhead Networks (acquired by Cisco). I was also involved in Dixon's startup Hunch (acquired by eBay), and have been a consultant to Bessemer Venture Partners, and a member of the Advanced Technology Advisory Council of PJM Interconnection. and the Scientific Advisory Board of Opera Solutions.

EDUCATION

I did my undergraduate studies at the University of California at Berkeley in math and computer science, graduating in 1985. I received a Ph.D. in computer science from Harvard University in 1989. The title of my dissertation was The Computational Complexity of Machine Learning (see Publications below for more information), and Les Valiant was my (superb) advisor. Following postdoctoral positions at the Laboratory for Computer Science at M.I.T. (hosted by Ron Rivest ) and at the International Computer Science Institute (ICSI) in Berkeley (hosted by Dick Karp ), in 1991 I joined the research staff of AT&T Bell Labs, and later the Penn faculty (see professional bio above).

Alongside my formal education, I was strongly influenced by being born into an academic family, including my father David Kearns (UCSD, Chemistry); his brother, and my uncle Tom Kearns (Amherst College, Philosophy); their father, and my paternal grandfather, Clyde Kearns (University of Illinois, Entomology); and my maternal grandfather Chen Shou-Yi (Pomona College, History and Literature).

EDITORIAL AND PROFESSIONAL SERVICE

In the past I have been program chair of NIPS, AAAI, COLT, and ACM EC. I have also served on the program committees of NIPS, AAAI, IJCAI, COLT, UAI, ICML, STOC, FOCS, and a variety of other acryonyms. I am a member of the NIPS Foundation, and was formerly on the steering committee for the Snowbird Conference on Learning (RIP).

I am on the editorial board of the MIT Press series on Adaptive Computation and Machine Learning, and the editorial board of the journal Market Microstructure and Liquidity. . In the past I have served on the editorial boards of Games and Economic Behavior, the Journal of the ACM, SIAM Journal on Computing, Machine Learning, the Journal of AI Research, and the Journal of Machine Learning Research.

I am currently a member of the Computer Science and Telecommunications Board of the National Academies.

From 2002-2008 I was a member, vice chair and chair of DARPA's Information Science and Technology (ISAT) study group.

RESEARCH GROUP

Current (alphabetical):

Occasionally visiting Caltech doctoral student Rachel Cummings
Doctoral student Hoda Heidari (jointly advised with Ali Jadbabaie )
Doctoral student Shahin Jabbari
Warren Center postdoc Jamie Morgenstern
Doctoral student Seth Neel (statistics department, jointly advised with Aaron Roth )
Doctoral student Ryan Rogers (jointly advised with Aaron Roth )
Warren Center postdoc Bo Waggoner
Doctoral student Steven Wu (jointly advised with Aaron Roth )
Research scientist Yuriy Nevmyvaka

Alumni (reverse chronological):

Former Warren Center postdoc Grigory Yaroslavtsev, now on the Indiana University CS faculty
Former doctoral student Lili Dworkin, now at Socratic
Former doctoral student Kareem Amin, now a postdoc at the University of Michigan
Former research scientist Stephen Judd
Former doctoral student Mickey Brautbar, now at Toast
Former postdoc Jake Abernethy, now on the University of Michigan CS faculty
Former postdoc Karthik Sridharan, now on the Cornell CS faculty
Former postdoc Kris Iyer, now on the Cornell ORIE faculty
Former MD/PhD student Renuka Nayak, now a clinical fellow at UCSF
Former doctoral student Tanmoy Chakraborty, now at Facebook
Former postdoc Umar Syed, now at Google NYC
Former doctoral student Jinsong Tan, now at Uber
Former postdoc Eugene Vorobeychik, now on the Vanderbilt CS faculty
Former postdoc Giro Cavallo, now at Yahoo! NYC
Former doctoral student Jenn Wortman Vaughan, now at Microsoft Research NYC
Former postdoc Eyal Even-Dar, now at Final Israel
Former doctoral student Sid Suri, now at Microsoft Research NYC
Former postdoc Sham Kakade, now on the University of Washington CS/stats faculty
Former postdoc Ryan Porter, now at AMA Capital
Former postdoc Luis Ortiz, now on the University of Michigan-Dearborn CS faculty
Former summer postdoctoral visitor John Langford, now at Microsoft Research NYC

Web page for the undergraduate course Networked Life (NETS 112), Fall 2015 and a condensed online version at Coursera.
(See also the Fall 2014,   Fall 2013,   Fall 2012,   Fall 2011 (hosted at Lore),   Spring 2010,   Spring 2009,   Spring 2008,   Spring 2007,   Spring 2006,   Spring 2005, and Spring 2004 offerings.)
Web page for MKSE 150: Market and Social Systems on the Internet, Spring 2013, taught jointly with Aaron Roth.
Web page for the graduate seminar No Regrets in Learning and Game Theory, Spring 2013, run jointly with Aaron Roth.
Here are the slides for my STOC 2012 tutorial on Algorithmic Trading and Computational Finance
Web page for CIS 625, Spring 2016: Computational Learning Theory. Here is an earlier version with Grigory Yaroslavtsev, an earlier version with Jake Abernethy, and an earlier version with Koby Crammer.
Web page for the graduate seminar course Social Networks and Algorithmic Game Theory, Fall 2009
Web page for CIS 620, Fall 2007: Seminar on Foundations of Cryptography.
Web page for CIS 620, Fall 2006: Seminar on Sponsored Search.
Web page for the graduate seminar CIS 700/04: Advanced Topics in Machine Learning (Fall 2004).
Web page for CIS 700/04: Advanced Topics in Machine Learning (Fall 2003).
Web page for a course on Computational Game Theory (Spring 2003). This was a joint course between CIS and Wharton (listed as CIS 620 and Wharton OPIM 952).
Course web page for CIS 620: Advanced Topics in AI (Spring 2002)
Course web page for CIS 620: Advanced Topics in AI (Spring 1997)
Web page for NIPS 2002 Tutorial on Computational Game Theory.
ACL 1999 Tutorial Slides [PDF]
Course Outline and Material for 1999 Bellairs Institute Workshop
Theoretical Issues in Probabilistic Artificial Intelligence (FOCS 98 Tutorial) [PDF]
A Short Course in Computational Learning Theory: ICML '97 and AAAI '97 Tutorials [PDF]

PRESS/MEDIA

Below are some press/media articles related to my work, or in which I am quoted. (Some links are unfortunately now dead.)

CBS Sunday Morning segment on "Luck",   September 2016.
Bloomberg news article on machine learning and macroeconomic policy, and a related radio segment on Bloomberg Surveillance,   June 2016.
Some coverage of the article Private Algorithms for the Protected in Social Network Search in Quartz,   Pacific Standard,   Motherboard,   Naked Scientists,   Groks Science,   PBS Newshour,   and upenn.edu,   Jan-June 2016.
MIT Technology Review article on Cloverpop, September 2014.
Bloomberg News article on HFT and hybrid quant funds, March 2014
Discussions of PAC and SQ learning and their relevance to evolution in Les Valiant's book "Probably Approximately Correct", June 2013
NPR text and audio on Coursera, online education, and Penn, October 2012
Australian radio program "Future Tense" on "The Algorithm", March 2012
Chapter on biased voting experiments in Garth Sundem's book "Brain Trust", 2012.
ScienceNews article on Princeton fish consensus experiments, December 2011.
A profile of and an interview with Les Valiant upon his receiving the 2010 Turing Award, CACM June 2011.
Profile and lecture overview, Christ's College Pieces, Lent Term 2011.
Fiscal Times article on machine learning and technology in trading, March 2011,
Wired Magazine article on algorithmic trading, January 2011, and some more extensive remarks and one-year follow-up on the author's blog.
Science News article on light speed propagation delays in trading, October 2010
Economist article on flash crash autopsy, October 2010
WSJ online post on HFT research, September 2010
Discussion of behavioral social network experiments in Peter Miller's "The Smart Swarm" (Chapter 3, page 139 forward)
Atlantic article on HFT "crop circles", August 2010
Nature News article on "distributed thinking", August 2010
Wall Street Journal article on machine learning in quant trading, July 2010 and a related interview on CNBC
New Scientist article on "Why Facebook friends are worth keeping", July 2010; here is a free reproduction
Philadelphia Business Journal article on the MKSE program and Networked Life, October 2009
Discussion of behavioral social network experiments in Christakis and Fowler's "Connected" (page 165 foward)
Philadelphia Inquirer article on networked voting experiments, March 2009
Science Daily article on networked voting experiments, February 2009
The Trade magazine article natural language processing for algorithmic trading, September 2007
Bloomberg Markets magazine article on AI on Wall Street, June 2007
SIAM News article on behavioral graph coloring, November 2006
Philadelphia Inquirer article on network science and NSA link analysis, May 2006
Chicago Tribune article on privacy in blogs and social networks, November 2005
Chronicle of Higher Education article on Facebook and social networks, May 2004
Star-Ledger article on the demise of AT&T Labs, March 2004
Business Week Online article on technology in NASDAQ and NYSE, September 2003
Philadelphia Inquirer article on ISTAR, interdependent security, and games on networks, January 2003
Washington Post article on web-based chatterbots, September 2002
New Scientist article on the Cobot spoken dialogue system, August 2002
Tornado Insider article on DDoS attacks, January 2002 [Cover]
Tornado Insider article on biometric security, January 2002
Audio of COMNET panel "Staving Off Denial-of-Service Attacks and Detecting Malicious Code"
Tornado Insider article on natural language technology, September 2001
Tornado Insider article on robotics, July 2001
Il Sole 24 Ore profile, June 2001 [English Translation]
Corriere Della Sera profile, May 2001 [English Translation]
Associated Press article on software robots, February 2001
New York Times article on TAC, August 2000
New York Times on Cobot, February 2000
TIME Digital Magazine (now Time On) on Cobot, May 2000
Washington Post article on Cobot, December 2000
New York Times article on boosting, August 1999

PUBLICATIONS:BOOKS

• An Introduction to Computational Learning Theory. Authored jointly with Prof. Umesh V. Vazirani of U.C. Berkeley, this MIT Press publication is intended to be an intuitive but precise treatment of some interesting and fundamental topics in computational learning theory. The level is appropriate for graduate students and researchers in machine learning, artificial intelligence, neural networks, and theoretical computer science. The link above is to the MIT Press page that provides a brief description of the book and ordering information. If you have the book and have any questions or comments, please click here to send me mail.
• The Computational Complexity of Machine Learning. This revision of my doctoral dissertation was published by the MIT Press as part of the ACM Doctoral Dissertation Award Series. As it is now out of print, I am making it available for downloading below.
  [PDF]

PUBLICATIONS: ARTICLES

What follows is a listing of (almost) all of my research papers in (approximately) reverse chronological order. For papers with both a conference and journal version, the paper is usually placed by its first (conference) date. Also, as per the honored tradition of the theoretical computer science community, on almost all of the papers below that are primarily mathematical in content, authors are listed alphabetically.

Acronyms for conferences and journals include: AAAI: Annual National Conference on Artificial Intelligence; AISTATS: International Conference on Artificial Intelligence and Statistics; ALT: Algorithmic Learning Theory; COLT: Annual Conference on Computational Learning Theory; EC: ACM Conference on Electronic Commerce; FOCS: IEEE Foundations of Computer Science; HCOMP: AAAI Conference on Human Computation and Crowdsourcing; ICML: International Conference on Machine Learning; IJCAI: International Joint Conference on Artificial Intelligence; ITCS: Innovations in Theoretical Computer Science; NIPS: Neural Information Processing Systems; PNAS: Proceedings of the National Academy of Science; SODA: ACM Symposium on Discrete Algorithms; STOC: ACM Symposium on the Theory of Computation; UAI: Annual Conference on Uncertainty in Artificial Intelligence; WINE: Workshop on Internet and Network Economics.

In addition to the list below, you can also look at my page on Google Scholar, and this DBLP query seems to do a pretty good job of finding those publications that appeared in mainstream CS venues (though not others), and can be useful for generating bibtex citations.

• Mathematical Foundations for Social Computing. With Yiling Chen, Arpita Ghosh, Tim Roughgarden, and Jennifer Wortman Vaughan. CACM, December 2016.
  [PDF]
• Fair Learning in Markovian Environments. With Shahin Jabbari, Matthew Joseph, Jamie Morgenstern, and Aaron Roth. Manuscript.
  [arXiv version]
• Rawlsian Fairness for Machine Learning With Matthew Joseph, Jamie Morgenstern, Seth Neel, and Aaron Roth. Manuscript.
  [arXiv version]
• Fairness in Learning: Classic and Contextual Bandits. With Matthew Joseph, Jamie Morgenstern, and Aaron Roth. NIPS 2016.
  [NIPS version] [arXiv version]
• Strategic Network Formation with Attack and Immunization. With S. Goyal, S. Jabbari, S. Khanna, and J. Morgenstern. WINE 2016.
  [arXiv version]
• Tight Policy Regret Bounds for Improving and Decaying Bandits. With Hoda Heidari and Aaron Roth. IJCAI 2016.
  [PDF]
• Private Algorithms for the Protected in Social Network Search. With A. Roth, S. Wu, and G. Yaroslavtsev. PNAS, January 2016.
  [PNAS version] [arXiv version]
• Robust Mediators in Large Games. With M. Pai, R. Rogers, A. Roth, and J. Ullman. Manuscript. (Subsumes and expands "Mechanism Design in Large Games: Incentives and Privacy", ITCS 2014).
  [arXiv version]
• The Small-World Network of Squash. With R. Rayfield. Squash Magazine, October 2015.
  [PDF] [online version]
• Privacy and Truthful Equilibrium Selection for Aggregative Games. With R. Cummings, A. Roth, and S. Wu. WINE 2015.
  [PDF] [arXiv version]
• From "In" to "Over": Behavioral Experiments on Whole-Network Computation. With L. Dworkin. HCOMP 2015.
  [PDF]
• Online Learning and Profit Maximization from Revealed Preferences. With K. Amin, R. Cummings, L.Dworkin, and A. Roth. AAAI 2015.
  [arXiv version] [AAAI version]
• Competitive Contagion in Networks. With H. Heidari and S. Goyal. To appear in Games and Economic Behavior. (This paper is an expanded version of the Goyal-Kearns STOC 2012 paper, and contains a number of new results.)
  [PDF]
• A Computational Study of Feasible Repackings in the FCC Incentive Auctions. With L.Dworkin. White paper filed with the Federal Communications Commission, June 2014.
  [PDF (on FCC website)] [Ex Parte Cover Letter]
• Pursuit-Evasion Without Regret, with an Application to Trading. With L.Dworkin and Y. Nevmyvaka. ICML 2014.
  [PDF]
• Learning from Contagion (Without Timestamps) With K. Amin and H. Heidari. ICML 2014.
  [PDF]
• New Models for Competitive Contagion. With M. Draief and H. Heidari. AAAI 2014.
  [PDF]
• Efficient Inference for Complex Queries on Complex Distributions. With L. Dworkin and L. Xia. AISTATS 2014.
  [PDF]
• Mechanism Design in Large Games: Incentives and Privacy With M. Pai, A. Roth, and J. Ullman. ITCS 2014.
  [PDF] [arXiv version]
• Marginals-to-Models Reducibility. With T. Roughgarden. NIPS 2013.
  [PDF]
• Machine Learning for Market Microstructure and High Frequency Trading. With Y. Nevmyvaka. In High Frequency Trading - New Realities for Traders, Markets and Regulators , M. O'Hara, M. Lopez de Prado, D. Easley, editors. Risk Books, 2013.
  [PDF] [publisher link]
• Stress-Induced Changes in Gene Interactions in Human Cells. With R. Nayak, W. Bernal, J. Lee, and V. Cheung. Nucleic Acids Research, 2013, 1-15.
  [PDF]
• Depth-Workload Tradeoffs for Workforce Organization. With H. Heidari. HCOMP 2013.
  [PDF]
• Large-Scale Bandit Problems and KWIK Learning. With J. Abernethy, K. Amin, and M. Draief. ICML 2013.
  [PDF]
• Experiments in Social Computation. Communications of the ACM, October 2012.
  [PDF] [CACM Issue]
• Budget Optimization for Sponsored Search: Censored Learning in MDPs. With K. Amin, P. Key and A. Schwaighofer. UAI 2012.
  [PDF]
• Behavioral Experiments on a Network Formation Game. With S. Judd and Y. Vorobeychik. ACM EC 2012.
  [PDF]
• Competitive Contagion in Networks. With S. Goyal. STOC 2012.
  [PDF]
• Colonel Blotto on Facebook: The Effect of Social Relations on Strategic Interaction. with P. Kohli, Y. Bachrach, D. Stillwell, R. Herbrich, T. Graepel. ACM Web Science, 2012.
  [PDF]
• Learning and Predicting Dynamic Behavior with Graphical Multiagent Models. With Q. Duong, M. Wellman, and S. Singh. AAMAS 2012.
  [PDF]
• Behavioral Conflict and Fairness in Social Networks. With S. Judd and E. Vorobeychik. WINE 2011.
  [PDF]
• A Clustering Coefficient Network Formation Game. With M. Brautbar. Symposium on Algorithmic Game Theory (SAGT), 2011.
  [PDF]
• Graphical Models for Bandit Problems. With K. Amin and U. Syed. UAI 2011.
  [PDF]
• Bandits, Query Learning, and the Haystack Dimension. With K. Amin and U. Syed. COLT 2011. (K. Amin, Best Student Presentation at NY Academy of Sciences ML workshop)
  [PDF]
• Market Making and Mean Reversion. With T. Chakraborty. ACM EC 2011.
  [PDF]
• Designing a Digital Future: Federally Funded Research and Development in Networking and Information Technology. PCAST Working Group. Report to the President and Congress, December 2010.
  [PDF] [Related Material]
• Empirical Limitations on High Frequency Trading Profitability. With A. Kulesza and Y. Nevmyvaka. Journal of Trading, Fall 2010. (JOT Best Paper Award for 2010)
  [SSRN version] [arXiv version] [JOT link]
• Behavioral Dynamics and Influence in Networked Coloring and Consensus. With S. Judd and Y. Vorobeychik. PNAS, August 2010.
  [PDF] [PNAS link]
• Private and Third-Party Randomization in Risk-Sensitive Equilibrium Concepts. With M. Brautbar, U. Syed. AAAI 2010.
  [PDF]
• A Behavioral Study of Bargaining in Social Networks. With T. Chakraborty, S. Judd, J. Tan. ACM EC 2010.
  [PDF]
• Local Algorithms for Finding Interesting Individuals in Large Networks. With M. Brautbar. Innovations in Theoretical Computer Science (ITCS), 2010.
  [PDF]
• Coexpression Network Based on Natural Variation in Human Gene Expression Reveals Gene Interactions and Functions. With R. Nayak, R. Spielman, V. Cheung. Genome Science, November 2009.
  [Web Link] [PDF] [Cover Image]
• Censored Exploration and the Dark Pool Problem. With K. Ganchev, Y. Nevmyvaka, J. Wortman. UAI 2009. Journal version in CACM, May 2010. (UAI Best Student Paper Award, K. Ganchev and J. Wortman)
  [PDF] [CACM version] [Peter Bartlett commentary] [BofA marketing summary]
• Networked Bargaining: Algorithms and Structural Results. With T. Chakraborty and S. Khanna. ACM EC 2009.
  [PDF]
• Behavioral Experiments on Biased Voting in Networks. With S. Judd, J. Tan and J. Wortman. PNAS, January 2009.
  [PDF]
• Biased Voting and the Democratic Primary Problem. With J. Tan. WINE 2008.
  [PDF]
• Bargaining Solutions in a Social Network. With T. Chakraborty. WINE 2008.
  [PDF]
• Learning from Collective Behavior. With J. Wortman. COLT 2008.
  [PDF]
• Behavioral Experiments in Networked Trade. With S. Judd. ACM EC 2008.
  [PDF]
• Graphical Games. In Algorithmic Game Theory, N. Nisan, T. Roughgarden, E. Tardos and V. Vazirani, editors, Cambridge University Press, September, 2007.
  [PDF]
• Sponsored Search with Contexts. With E. Even-Dar and J. Wortman. WINE 2007. The following longer version appeared in the Third Workshop on Sponsored Search Auctions, WWW 2007.
  [PDF]
• Empirical Price Modeling for Sponsored Search. With K. Ganchev, A. Kulesza, J. Tan, R. Gabbard, Q. Liu. WINE 2007. The following longer version appeared in the Third Workshop on Sponsored Search Auctions, WWW 2007.
  [PDF]
• A Network Formation Game for Bipartite Exchange Economies. With E. Even-Dar and S. Suri. ACM SODA 2007.
  [PDF] [Extended Version, PDF]
• Privacy-Preserving Belief Propagation and Sampling. With J. Tan and J. Wortman. NIPS 2007.
  [PDF]
• Regret to the Best vs. Regret to the Average. With E. Even-Dar, Y. Mansour, and J. Wortman. COLT 2007. (J. Wortman, COLT Best Student Paper Award)
  [PDF]
• A Small World Threshold for Economic Network Formation. With E. Even-Dar. NIPS 2006.
  [PDF]
• An Experimental Study of the Coloring Problem on Human Subject Networks. With S. Suri and N. Montfort. Science 313(5788), August 2006, pp. 824-827.
  [Abstract]   [Full Paper]   [PDF]
• Networks Preserving Evolutionary Stability and the Power of Randomization. With S. Suri. ACM Conference on Electronic Commerce (EC), 2006.
  [PDF]
• (In)Stability Properties of Limit Order Dynamics. With E. Even-Dar, S. Kakade, and Y. Mansour. ACM Conference on Electronic Commerce (EC), 2006.
  [PDF]
• Reinforcement Learning for Optimized Trade Execution. With Y. Nevmyvaka and Y. Feng. ICML 2006.
  [PDF]
• Risk-Sensitive Online Learning. With E. Even-Dar and J. Wortman. ALT 2006. This is a corrected version posted Oct 4 2006. This version corrects errors in the section of experimental results published in the ALT 2006 proceedings.
  [PDF]
• Learning from Multiple Sources. With K. Crammer and J. Wortman. NIPS 2006; also in JMLR 2008.
  [PDF] [Journal Version PDF]
• Economics, Computer Science, and Policy.
  Issues in Science and Technology, Winter 2005.
  [Article in PDF]
  [Cover Image]

• Electronic Trading in Order-Driven Markets: Efficient Execution. With Y. Nevmyvaka, A. Papandreou and K. Sycara. IEEE Conference on Electronic Commerce (CEC), 2005.
  [PDF]
• Trading in Markovian Price Models. With S. Kakade. COLT 2005.
  [PDF]
• Learning from Data of Variable Quality. With K. Crammer and J. Wortman. NIPS 2005.
  [PDF]
• Economic Properties of Social Networks. With S. Kakade, L. Ortiz, R. Pemantle, and S. Suri. Proceedings of NIPS 2004.
  [PDF]
• Graphical Economics. With S. Kakade and L. Ortiz. Proceedings of COLT 2004.
  [PDF]
• Competitive Algorithms for VWAP and Limit Order Trading. With S. Kakade, Y. Mansour and L. Ortiz. Proceedings of the ACM Conference on Electronic Commerce (EC), 2004.
  [PDF]
• Algorithms for Interdependent Security Games. With L. Ortiz. NIPS 2003.
  [PDF]
• Correlated Equilibria in Graphical Games. With S. Kakade, J. Langford, and L. Ortiz. ACM Conference on Electronic Commerce (EC), 2003.
  [PDF]
• The Penn-Lehman Automated Trading Project. With L. Ortiz. IEEE Intelligent Systems, Nov/Dec 2003.
  IEEE version [PDF] Long version [PDF]
• Exploration in Metric State Spaces. With S. Kakade and J. Langford. ICML 2003.
  [PDF]
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System. With S. Singh, D. Litman, M. Walker. Journal of Artificial Intelligence Research, 2002.
  [PDF]
• Nash Propagation for Loopy Graphical Games. With L. Ortiz. Proceedings of NIPS 2002.
  [PDF]
• Efficient Nash Computation in Large Population Games with Bounded Influence. With Y. Mansour. Proceedings of UAI 2002.
  [PDF]
• A Note on the Representational Incompatabilty of Function Approximation and Factored Dynamics. With E. Allender, S. Arora, C. Moore, A. Russell. Proceedings of NIPS 2002.
  [PDF]
• CobotDS: A Spoken Dialogue System for Chat. With C. Isbell, S. Singh, D. Litman, J. Howe. Proceedings of AAAI 2002.
  [PDF]
• An Efficient Exact Algorithm for Singly Connected Graphical Games. With M. Littman, S. Singh. 2001. NIPS 2001.
  [PDF]

NOTE: The main result of the paper above --- an efficient algorithm claimed to find a single exact Nash equilibrium in tree graphical games --- is unfortunately wrong. This was discovered and discussed in the very nice paper by Elkind, Goldberg and Goldberg, which can be found here. The problem of efficiently computing an exact Nash equilibrium in trees remains open (though EG&G demonstrate that no two-pass algorithm can suffice). The original polynomial-time approximate Nash algorithm from the K., Littman, Singh UAI 2001 paper is unaffected by these developments, as is its NashProp generalization in the Ortiz and K. 2002 NIPS paper.

• Graphical Models for Game Theory. With M. Littman, S. Singh. 2001. UAI 2001.
  [PDF]
• ATTac-2000: An Adaptive Autonomous Bidding Agent. With P. Stone, M. Littman, S. Singh. Journal of Artificial Intelligence Research . Earlier version in Proceedings of Agents 2001.
  [PDF]
  New York Times article on TAC
• A Social Reinforcement Learning Agent. With C. Shelton, C. Isbell, S. Singh, P. Stone. Proceedings of Agents 2001. Winner of Best Paper Award at the Conference.
  [PDF]
• Nash Convergence of Gradient Dynamics in General-Sum Games. With S. Singh, Y. Mansour. Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, pages 541-548, 2000.
  [PDF]
• Fast Planning in Stochastic Games. With Y. Mansour, S. Singh. Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, pages 309-316, 2000.
  [PDF]
• Bias-Variance Error Bounds for Temporal Difference Updates. With S. Singh. Proceedings of the 13th Annual Conference on Computational Learning Theory, 2000, pages 142--147.
  [PDF]
• Approximate Planning in Large POMDPs via Reusable Trajectories. With Y. Mansour and A. Ng. Advances in Neural Information Processing Systems 12, MIT Press, 2000.
  [PDF] [Long Version]
• Testing Problems with Sub-Learning Sample Complexity. With D. Ron. Journal of Computer and System Sciences, 61, pp. 428-456, 2000. Earlier version in Proceedings of the 12th Annual Workshop on Computational Learning Theory.
  [PDF]
• Cobot in LambdaMOO: A Social Statistics Agent. With C. Isbell, D. Kormann, S. Singh, P. Stone. Proceedings of the 17th National Conference on Artificial Intelligence, pp. 36-41, 2000, AAAI Press/MIT Press.
  [PDF]
• Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System. With S. Singh, D. Litman, M. Walker. Proceedings of the 17th National Conference on Artificial Intelligence, pp. 645-651, 2000, AAAI Press/MIT Press.
  [PDF]
• Automatic Optimization of Dialogue Management. With D. Litman, S. Singh, M. Walker. Appeared in COLING 2000.
  [PDF]
• A Boosting Approach to Topic Spotting on Subdialogues. With K. Myers, S. Singh, M. Walker. Appeared in ICML 2000.
  [PDF]
• Reinforcement Learning for Spoken Dialogue Systems. With S. Singh, D. Litman and M. Walker. Advances in Neural Information Processing Systems 12, MIT Press, 2000.
  [PDF]
• Automatic Detection of Poor Speech Recognition at the Dialogue Level. With D. Litman and M. Walker. Proceedings of the 37th Annual Meeting for Computational Linguistics, 1999, pages 309-316.
  [PDF]
• A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes. With Y. Mansour and A. Ng. Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence Morgan Kaufmann, 1999, pages 1324--1331. Also appeared in a special issue of the journal Machine Learning, 2002.
  [PDF, Journal Version]
• Efficient Reinforcement Learning in Factored MDPs. With D. Koller. Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann, 1999, pages 740--747.
  [PDF]
• Finite-Sample Rates of Convergence for Q-Learning and Indirect Methods. With S. Singh. Advances in Neural Information Processing Systems 11, The MIT Press, 1999, pages 996--1002.
  [PDF]
• Inference in Multilayer Networks via Large Deviation Bounds. with L. Saul. Advances in Neural Information Processing Systems 11, The MIT Press, 1999, pages 260--266.
  [PDF]
• Large Deviation Methods for Approximate Probabilistic Inference, with Rates of Convergence. With L. Saul. Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, 1998, pages 311--319.
  [PDF]
• Exact Inference of Hidden Structure from Sample Data in Noisy-OR Networks. With Y. Mansour. Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, 1998, pages 304--310.
  [PDF]
• Near-Optimal Reinforcement Learning in Polynomial Time. With S. Singh. Proceedings of the 15th International Conference on Machine Learning, pp. 260-268, 1998, Morgan Kaufmann. Appeared in a special issue of the journal Machine Learning.
  [PDF]
• A Fast, Bottom-Up Decision Tree Pruning Algorithm with Near-Optimal Generalization. With Y. Mansour. Proceedings of the 15th International Conference on Machine Learning, 1998, Morgan Kaufmann, pages 269--277.
  [PDF]
• An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering. with Y. Mansour and A. Ng. Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence, pp. 282-293, 1997, Morgan Kaufmann.
  [PDF]
• Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-Validation. With D. Ron. Neural Computation 11(6), pages 1427-1453, 1999. Earlier version in Proceedings of the Tenth Annual Conference on Computational Learning Theory, ACM Press, 1997, pages 152--162.
  [PDF]
• Boosting Theory Towards Practice: Recent Developments in Decision Tree Induction and the Weak Learning Framework. Abstract accompanying invited talk given at AAAI '96, Portland, Oregon, August 1996.
  [PDF]
• Applying the Weak Learning Framework to Understand and Improve C4.5. With T. Dietterich and Y. Mansour. Proceedings of the 13th International Conference on Machine Learning, pp. 96-104, 1996, Morgan Kaufmann.
  [PDF]
• On the Boosting Ability of Top-Down Decision Tree Learning Algorithms. With Y. Mansour. Journal of Computer and Systems Sciences, 58(1), 1999, pages 109-128. Earlier version in Proceedings of the 28th ACM Symposium on the Theory of Computing, pp.459-468, 1996, ACM Press.
  [PDF]
• A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for the Training-Test Split. Neural Computation 9(5), 1997, pages 1143--1161. Earlier version in Advances in Neural Information Processing Systems 8, The MIT Press, pages 183--189, 1996.
  [PDF]
• An Experimental and Theoretical Comparison of Model Selection Methods. With Y. Mansour, A. Ng, and D. Ron. Machine Learning 27(1), 1997, pages 7--50. Earlier version in Proceedings of the Eighth ACM Conference on Computational Learning Theory, ACM Press, 1995, pages 21--30.
  [COLT version] [MLJ version]
• On the Consequences of the Statistical Mechanics Theory of Learning Curves for the Model Selection Problem. Neural Networks: The Statistical Mechanics Perspective, pp. 277-284, 1995, World Scientific.
  [PDF]
• Efficient Algorithms for Learning to Play Repeated Games Against Computationally Bounded Adversaries. With Y. Freund, Y. Mansour, D. Ron, R. Rubinfeld, and R. Schapire. Proceedings of the 36th IEEE Symposium on the Foundations of Computer Science, pp. 332-341, 1995, IEEE Press.
  [PDF]
• Horn Approximations of Empirical Data. With H. Kautz and B. Selman. Artificial Intelligence, 74(1), pages 129-145, 1995.
  [PDF]
• On the Complexity of Teaching. With S. Goldman. Journal of Computer and Systems Sciences, 50(1), pp. 20-31, 1995.
  [PDF]
• On the Learnability of Discrete Distributions. With Y. Mansour, R. Rubinfeld, D. Ron, R. Schapire, and L. Sellie. Proceedings of the 26th Annual ACM Symposium on the Theory of Computing, pp. 273-282, 1994, ACM Press.
  [PDF]
• Cryptographic Primitives Based on Hard Learning Problems. With A. Blum, M. Furst, and R. Lipton. Advances in Cryptology, Lecture Notes in Computer Science, Volume 773, pp. 278-291, 1994, Springer-Verlag.
  [PDF]
• Rigorous Learning Curve Bounds from Statistical Mechanics. With D. Haussler, H.S. Seung, and N. Tishby. Machine Learning,25, 1996, pages 195--236. Earlier version in ACM Conference on Computational Learning Theory, pp. 76-87, 1994, ACM Press.
  [PDF]
• The Minimal Disagreement Parity Problem as a Hard Satisfiability Problem. With J. Crawford and R. Schapire. Unpublished manuscript, 1994.
  [PDF]
• Weakly Learning DNF and Characterizing Statistical Query Learning Using Fourier Analysis. With A. Blum, M. Furst, J. Jackson, Y. Mansour, and S. Rudich. Proceedings of the 26th Annual ACM Symposium on the Theory of Computing, pp. 253-262, 1994, ACM Press.
  [PDF]
• Efficient Noise-Tolerant Learning from Statistical Queries. Journal of the ACM , 45(6), pp. 983 --- 1006, 1998. Earlier version in Proceedings of the 25th ACM Symposium on the Theory of Computing, pp. 392-401, 1993, ACM Press.
  [PDF]
• Efficient Learning of Typical Finite Automata from Random Walks. With Y. Freund, D. Ron, R. Rubinfeld, R. Schapire, and L. Sellie. Proceedings of the 25th ACM Symposium on the Theory of Computing, pp. 315-324, 1993, ACM Press.
  [PDF]
• Learning from a Population of Hypotheses. With S. Seung. Machine Learning 18, pp. 255-276, 1995. Earlier version in Proceedings of the Sixth Annual Workshop on Computational Learning Theory, pp. 101-110, 1993, ACM Press.
  [PDF]
• Towards Efficient Agnostic Learning. With R. Schapire and L. Sellie. Machine Learning 17, pp. 115-141, 1994. Earlier version in Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp. 341-352, 1992, ACM Press.
  [PDF]
• Bounds on the Sample Complexity of Bayesian Learning Using Information Theory and the VC Dimension. With D. Haussler and R. Schapire. Machine Learning 14, pp. 83-113, 1994. Earlier version in Proceedings of the Fourth Annual Workshop on Computational Learning Theory, pp. 61-74, 1991, Morgan Kaufmann.
  [PDF]
• Oblivious PAC Learning of Concept Hierarchies. AAAI 1992.
  [PDF]
• Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics, and VC Dimension Methods. With D. Haussler, M. Opper, and R. Schapire. NIPS 1991.
  [PDF]
• Equivalence of Models for Polynomial Learnability. With D. Haussler, N. Littlestone, and M. Warmuth. Information and Computation 95(2), pp. 129-161, 1991.
  [PDF]
• Efficient Distribution-free Learning of Probabilistic Concepts. With R. Schapire. Journal of Computer and System Sciences 48(3), pp. 464-497. Earlier version in Proceedings of the 31st Annual IEEE Symposium on Foundations of Computer Science, pp. 382-391, 1990, IEEE Press.
  [PDF]
• Exact Identification of Read-once Formulas Using Fixed Points of Amplification Functions. With S. Goldman and R. Schapire. SIAM Journal on Computing 22(4), pp. 705-726. Earlier version in Proceedings of the 31st IEEE Symposium on Foundations of Computer Science, pp. 193-202, 1990, IEEE Press.
  [PDF]
• A Polynomial-Time Algorithm for Learning k-Variable Pattern Languages from Examples. With L. Pitt. COLT 1989. (Unfortunately missing references, bib file got corrupted)
  [PDF]
• Cryptographic Limitations on Learning Boolean Formulae and Finite Automata. With L. Valiant. Journal of the ACM 41(1), pp. 67-95, 1994. Earlier version in Proceedings of the 21st ACM Symposium on the Theory of Computing, pp. 433-444, 1989, ACM Press.
  [PDF]
• A General Lower Bound on the Number of Examples Needed for Learning. With A. Ehrenfeucht, D. Haussler, and L. Valiant. Information and Computation 82(3), pp. 247-261, 1989. Earlier version in Proceedings of the 1988 Workshop on Computational Learning Theory, pp. 139-154, 1988, Morgan Kaufmann.
  [PDF]
• Learning in the Presence of Malicious Errors. With M. Li. SIAM Journal on Computing 22(4), pp. 807-837, 1993. Earlier version in Proceedings of the 20th ACM Symposium on the Theory of Computing, pp. 267-280, 1988, ACM Press.
  [PDF]
• Thoughts on Hypothesis Boosting. Unpublished manuscript, 1988. Project for Ron Rivest's machine learning course at MIT.
  [PDF]
• On the Learnability of Boolean Formulae. With M. Li, L. Pitt, and L. Valiant. Proceedings of the 19th ACM Symposium on the Theory of Computing, pp. 285-195, 1987, ACM Press.
  [PDF]
• Learning Boolean Formulae. With M. Li and L. Valiant. Journal of the ACM 41(6), pp. 1298-1328, 1995. Earlier version in Proceedings of the 19th ACM Symposium on the Theory of Computing, pp. 285-195, 1987, ACM Press.
  [PDF]
• Recent Results in Boolean Concept Learning. With M. Li, L. Pitt and L. Valiant. Proceedings of the Fourth International Workshop on Machine Learning, pp. 337-352, 1987, Morgan Kaufmann.
  [PDF]

Last Modified: December 31, 2016

WM 3YC