[PHOTO]                             MICHAEL KEARNS

Professor of Computer and Information Science
University of Pennsylvania
National Center Chair in Resource Management and Technology
Secondary Appointment, Operations and Information Management,   Wharton School

509 Levine Hall
3330 Walnut Street
Philadelphia, PA 19104-6389
Phone: (215)898-7888
Fax: (215)573-8190

Mobile: (201)936-6924
Penn email: mkearns@cis.upenn.edu

CIS administrative assistant:
Cheryl Hickey
Phone: (215)898-3538
Email: cherylh@cis.upenn.edu

                        [PHOTO]

QUICK LINKS

Quick link to Publications.
Quick link to the web page for the undergraduate course Networked Life (CIS 112), Spring 2008.
Quick link to the web page for CIS 620, Fall 2007: Seminar on Foundations of Cryptography.
Quick link to the web page for CIS 620, Fall 2006: Seminar on Sponsored Search.
Quick link to web page for the Penn-Lehman Automated Trading Project. (Currently inactive, but hope to revive someday.)

SITE DIRECTORY

Out of either a heightened design aesthetic or laziness (you be the judge), most of this site is organized as a single flat html file. The links below let you navigate directly to the various subsections.

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

RESEARCH INTERESTS

My primary research interests are in machine learning, probabilistic artificial intelligence, algorithmic game theory, and computational finance. I often blend problems from these areas with methods from theoretical computer science and related disciplines. While the majority of my work is mathematical in nature, I have also participated in a variety of systems and experimental work, including spoken dialogue systems, software agents, and human-subject experiments in strategic interaction.

BRIEF 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 in Resource Management and Technology. I also have a secondary appointment in the Operations and Information Management (OPIM) department of the Wharton School, and until July 2006 was the co-director of Penn's interdisciplinary Institute for Research in Cognitive Science.

I also lead the Systematic Trading group of Bank of America Securities in New York City. The group is part of BofA's Electronic Trading Services division. (For BofA-related business, please send me email at michael.kearns@bofasecurities.com)

I serve as an advisor to the companies Yodle and Invite Media, and am a member of the Advanced Technology Advisory Council of PJM Interconnection.

The Past:

I spent the decade 1991-2001 in basic AI and machine learning research at Bell Labs and AT&T 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. The department offered terrific colleagues and friends that included Charles Isbell (now at Georgia Tech), Diane Litman (now at University of Pittsburgh), Michael Littman (now at Rutgers), 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 department was shaped by the efforts of a number of notable figures, including Ron Brachman (who originally founded the deparment; 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 (now also at Penn), and included Michael Collins (now at MIT), Sanjoy Dasgupta (now at UCSD), Yoav Freund (now at UCSD), Rob Schapire (now at Princeton), William Cohen (now at CMU), and Yoram Singer (now at Hebrew University and Google). Other friends and colleagues from Labs days include Sebastian Seung (now at MIT), Lawrence Saul (now at UCSD), Yann LeCun (now at NYU), Roberto Pieraccini (now at SpeechCycle), Esther Levin (now at CCNY), Lyn Walker (now at the University of Sheffield), Corinna Cortes (now at Google), and Vladimir Vapnik (now at Columbia and NEC). Suffice to say we all had a great time together.

During my time at AT&T/Bell Labs, I also served briefly as the head of the Secure Systems Research department.

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

From the Spring of 2002 through May 2007, I was both a consultant to and the head of a quant team within the Equity Strategies group of Lehman Brothers in New York City.

I have also served on the technical advisory board of SiteAdvisor (founded by Chris Dixon), and as a consultant to Bessemer Venture Partners.  

EDUCATIONAL BACKGROUND

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 advisor. Following postdoctoral positions at the Laboratory for Computer Science at M.I.T. and at the International Computer Science Institute in Berkeley, in 1991 I joined the research staff of AT&T Bell Labs and later the Penn faculty (see professional bio above).

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 the steering committee for the Snowbird Conference on Learning.

I am currently on the editorial boards of Mathematics of Operations Research, Games and Economic Behavior, the Journal of the ACM, and the MIT Press series on Adaptive Computation and Machine Learning. In the past I have also served on the editorial boards of SIAM Journal on Computing, Machine Learning, the Journal of AI Research, and the Journal of Machine Learning Research.

I am the chair of DARPA's Information Science and Technology (ISAT) study group.

RESEARCH GROUP MEMBERS

Current:

Doctoral student Jenn Wortman
Doctoral student Jinsong Tan
Research scientist Stephen Judd
MD/PhD student Renuka Nayak (works primarily in the lab of Vivian Cheung )
Postdoc Koby Crammer (mainly works with Fernando Pereira)

Alumni:

Former summer visitor Nina Balcan
Former postdoc Eyal Even-Dar, now at Google
Former doctoral student Sid Suri, now a postdoc at Cornell
Former postdoc Sham Kakade, now on the faculty of TTI-Chicago
Former postdoc Ryan Porter, now at Amazon
Former postdoc Luis Ortiz, now at MIT
Former summer postdoctoral visitor John Langford, now at Yahoo! Research

TEACHING AND TUTORIAL MATERIAL

Web page for CIS 620, Fall 2007: Seminar on Foundations of Cryptography.
Web page for Networked Life, Spring 2008. See also the Spring 2007,   Spring 2006,   Spring 2005, and Spring 2004 offerings.
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 [Postscript] [Compressed Postscript] [PDF]
Course Outline and Material for 1999 Bellairs Institute Workshop
Theoretical Issues in Probabilistic Artificial Intelligence (FOCS 98 Tutorial) [Postscript] [Compressed Postscript] [PDF]
A Short Course in Computational Learning Theory: ICML '97 and AAAI '97 Tutorials [Postscript] [Compressed Postscript] [PDF]

PRESS

Following are links to popular press articles that I either wrote, am quoted in, or are about research projects in which I participated.

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 thefacebook.com 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

[PHOTO]--

PUBLICATIONS: RESEARCH ARTICLES

What follows is a listing of almost all of my research papers in several formats. (Feel free to contact me if you need a different format.) Papers are grouped by approximate topic, then chronologically within topic. Some papers may appear under more than one topic. Links to my more recent papers are grouped at the top for convenience, then repeated under their topic(s).

The topics are:

More Recent Papers
Computational Game Theory, Economics, and Multi-Agent Systems
Computational Finance and Market Microstructure
Reinforcement Learning and Markov Decision Processes
Probabilistic Inference, Graphical Models, Distribution Learning
Online Learning
Decision Tree Learning and Boosting
Learning Curves and Sample Complexity
Model Selection and Complexity Regularization
Learning in the Presence of Noise and Errors
Agnostic Learning and Probabilistic Concepts
Cryptography and Learning
Learning Finite Automata
Early Results in PAC Learning
Miscellaneous Learning Theory
Agents in Chat Environments (The Cobot Project)
Spoken Dialogue Systems

MORE RECENT PAPERS:

COMPUTATIONAL GAME THEORY, ECONOMICS, AND MULTI-AGENT SYSTEMS:

COMPUTATIONAL FINANCE AND MARKET MICROSTRUCTURE:

REINFORCEMENT LEARNING AND MARKOV DECISION PROCESSES:

PROBABILISTIC INFERENCE, GRAPHICAL MODELS, DISTRIBUTION LEARNING:

ONLINE LEARNING :

DECISION TREE LEARNING AND BOOSTING:

LEARNING CURVES AND SAMPLE COMPLEXITY:

MODEL SELECTION AND COMPLEXITY REGULARIZATION:

LEARNING IN THE PRESENCE OF NOISE AND ERRORS:

AGNOSTIC LEARNING AND PROBABILISTIC CONCEPTS:

CRYPTOGRAPHY AND LEARNING:

LEARNING FINITE AUTOMATA:

EARLY RESULTS IN PAC LEARNING:

MISCELLANEOUS LEARNING THEORY:

AGENTS IN CHAT ENVIRONMENTS (The Cobot Project): SPOKEN DIALOGUE SYSTEMS:

Last Edited: April 15, 2008


www.digits.com

WM 3YC