Is Upenn Good For Machine Learning

For (in)convenience, most of this site is organized equally a single flat html file. The links beneath let you navigate directly to the diverse subsections.

Aaron Roth and I accept written a general-audition volume about the science of designing algorithms that embed social values like privacy and fairness; hither is the publisher's clarification:

Over the class of a generation, algorithms take gone from mathematical abstractions to powerful mediators of daily life. Algorithms accept made our lives more efficient, more than entertaining, and, sometimes, better informed. At the same fourth dimension, complex algorithms are increasingly violating the basic rights of individual citizens. Allegedly anonymized datasets routinely leak our nearly sensitive personal information; statistical models for everything from mortgages to college admissions reflect racial and gender bias. Meanwhile, users manipulate algorithms to "game" search engines, spam filters, online reviewing services, and navigation apps.

Understanding and improving the scientific discipline backside the algorithms that run our lives is rapidly becoming one of the most pressing issues of this century. Traditional fixes, such as laws, regulations and watchdog groups, accept proven woefully inadequate. Reporting from the cutting edge of scientific research, The Ethical Algorithm offers a new approach: a set of principled solutions based on the emerging and exciting science of socially enlightened algorithm design. Michael Kearns and Aaron Roth explain how nosotros tin improve embed human principles into motorcar code - without halting the advance of information-driven scientific exploration. Weaving together innovative inquiry with stories of citizens, scientists, and activists on the front end lines, The Upstanding Algorithm offers a compelling vision for a future, one in which we can better protect humans from the unintended impacts of algorithms while continuing to inspire wondrous advances in technology.

An opinion slice adapted from book themes in Scientific American.

Research INTERESTS

My inquiry interests include topics in car learning, algorithmic game theory and microeconomics, computational social science, and quantitative finance and algorithmic trading. I oftentimes examine problems in these areas using methods and models from theoretical information science and related disciplines. While much of my work is mathematical in nature, I also frequently participate in empirical and experimental projects, including applications of motorcar learning to bug in algorithmic trading and quantitative finance, and human-subject experiments on strategic and economic interaction in social networks.

QUICK LINKS

Didactics Spring 2022: CIS 423/523, Upstanding Algorithm Design.
Teaching Fall 2021: CIS 625, Theory of Machine Learning.
Warren Center for Network and Information Sciences
Networked and Social Systems Engineering (NETS) Program
Penn undergraduate course Networked Life (NETS 112), Fall 2019 and a condensed video version.
Penn-Lehman Automated Trading Project (inactive)
Tribute Twenty-four hours for Les Valiant, May 2009

Videos of some miscellaneous talks:

"Algorithmic Trading: The Machine Learning Approach", (Quantcon 2015, technical)

Brief Professional BIO

Current:

Since 2002 I have been a professor in the Computer and Data Science Department at the University of Pennsylvania, where I hold the National Center Chair. I have secondary appointments in the department of Economic science, and in the departments of Statistics and Data Science and Operations, Information and Decisions (OID) in the Wharton Schoolhouse. 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 manager of Penn Engineering's Networked and Social Systems Engineering (NETS) Program, whose current directors are Andreas Haeberlen and Aaron Roth. I am a kinesthesia affiliate in Penn's Applied Math and Computational Science graduate programme. Until July 2006 I was the co-director of Penn's interdisciplinary Establish for Research in Cognitive Science.

Since June 2020, I am an Amazon Scholar, focusing on fairness and privacy in machine learning and related topics within Amazon Web Services.

I accept worked extensively in quantitative and algorithmic trading on Wall Street (including at Lehman Brothers, Bank of America, SAC Capital and Morgan Stanley; see further details below). I often serve as an advisor to technology companies and venture capital firms, and sometimes invest in early-stage technology startups. I occasionally serve as an expert witness or consultant on technology-related legal and regulatory cases.

I am an elected Member/Fellow of the National Academy of Sciences, the American University of Arts and Sciences, the Association for Computing Mechanism, the Association for the Advocacy of Artificial Intelligence, and the Society for the Advancement of Economical Theory.

The Past:

I spent the decade 1991-2001 in machine learning and AI research at AT&T Bell Labs. During my terminal iv years at that place, I was the head of the AI section, which conducted a broad range of systems and foundational AI piece of work; I besides served briefly as the head of the Secure Systems Research department. The AI department boasted terrific colleagues and friends that included Charles Isbell (at present at Georgia Tech), Diane Litman (now at University of Pittsburgh), Michael Littman (later at Rutgers, at present at Brown), David McAllester (now at TTI-Chicago), Satinder Singh (at present at Academy 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 Cornell Tech), Henry Kautz (who led the section before heading to the University of Washington; now at the Academy of Rochester), and Bart Selman (now at Cornell). Earlier leading the AI group, I was a fellow member of the closely related Car Learning department at the labs, which was headed by Fernando Pereira (after at Penn, at present at Google), and included Michael Collins (later at MIT and Columbia, now at Google), Sanjoy Dasgupta (at present at UCSD), Yoav Freund (now at UCSD), Rob Schapire (subsequently at Princeton, at present at Microsoft Research), William Cohen (now at CMU), and Yoram Singer (after at Hebrew University and Google, at present at Princeton). Other friends and colleagues from Labs days include Sebastian Seung (afterwards at MIT, now at Princeton), Lawrence Saul (afterward at Penn, now at UCSD), Yann LeCun (now at Facebook and NYU), Roberto Pieraccini (now at Jibo), Esther Levin (at present at Point72), Lyn Walker (now at UC Santa Cruz), Corinna Cortes (now at Google), and Vladimir Vapnik (now at Facebook).

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

From June 2018 to June 2020, I led applied research in the AI Center of Excellence at Morgan Stanley, along with Yuriy Nevmyvaka (with whom I have also collaborated on a number of papers on algorithmic trading ).

From June 2016 to March of 2018, I was the Chief Scientist of MANA Partners, a trading, engineering and asset management firm based in NYC. From early 2014 to June 2016, I led a quantitative portfolio direction team with Yuriy Nevmyvaka at Engineers Gate. From June 2009 through September 2013, we were PMs in the MultiQuant division of SAC Majuscule in New York Metropolis. From May 2007 through Apr 2009, nosotros led a quantitative trading squad at Banking company of America in New York City, working on both proprietary and algorithmic trading strategies within BofA's Electronic Trading Services division. From the Bound of 2002 through May 2007, I was get-go a consultant to, and later the caput of, a quant prop trading squad inside the Disinterestedness 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 Swain at Christ'due south College. I also spent time visiting Microsoft Inquiry Cambridge.

I have served every bit an advisor to the startups Yodle (caused by web.com), Wealthfront, Actuate Networks, RootMetrics (acquired by IHS), Convertro (acquired by AOL), Invite Media (acquired by Google), SiteAdvisor (founded past Chris Dixon; acquired by McAfee), PayNearMe (formerly known every bit Kwedit), and Riverhead Networks (acquired past Cisco). I was also involved in Dixon'due south startup Hunch (caused by eBay), and have been a consultant to Bessemer Venture Partners.

In the by I take served as a member of the Advanced Engineering Advisory Council of PJM Interconnection. the Scientific Advisory Board of Opera Solutions, and the Technical Advisory Lath of Microsoft Research Cambridge. I am a erstwhile member of the Scientific Advisory Lath of the Alan Turing Institute, and of the Marketplace Surveillance Advisory Grouping of FINRA, and a former external faculty member at the Santa Atomic number 26 Plant.

Teaching

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 calculator science from Harvard University in 1989. The title of my dissertation was The Computational Complexity of Motorcar Learning (see Publications below for more information), and Les Valiant was my (superb) advisor. Post-obit postdoctoral positions at the Laboratory for Estimator Science at M.I.T. (hosted past Ron Rivest ) and at the International Information science Constitute (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).

Aslope my formal teaching, I was strongly influenced past being raised in an academic family, which included my father David R. Kearns (UCSD, Chemistry); his brother, and my uncle Thomas R. Kearns (Amherst Higher, Philosophy); their father, and my paternal granddaddy, Clyde W. Kearns (University of Illinois, Entomology); and my maternal grandfather Chen Shou-Yi (Pomona College, Chinese History and Literature).

EDITORIAL AND Professional SERVICE

In the by I take been program chair or co-chair of ACM FAccT, NIPS, AAAI, Colt, and ACM EC. I have besides served on the program committees of NIPS, AAAI, IJCAI, COLT, UAI, ICML, STOC, FOCS, and a diverseness of other acryonyms. I am a member of the NIPS Foundation, and was formerly on the steering committee for the Snowbird Briefing on Learning (RIP).

I am on the editorial board of the MIT Printing series on Adaptive Computation and Machine Learning, and the editorial board of the journals PNAS Nexus and Marketplace 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 Inquiry, and the Journal of Auto Learning Inquiry.

I am currently a member of the Emerging Technology Technical Advisory Committee of the U.S. Section of Commerce.

I am a former member of the Computer Science and Telecommunications Lath of the National Academies. From 2002-2008 I was a member, vice chair and chair of DARPA'south Data Science and Technology (ISAT) report group.

RESEARCH Grouping

Current (alphabetical):

Doctoral student Natalie Collina (jointly advised with Aaron Roth )
Doctoral student Emily Diana
Doctoral student Ira Globus-Harris (jointly brash with Aaron Roth )
Doctoral student Varun Gupta (jointly advised with Aaron Roth )
Doctoral student Chris Jung (jointly advised with Aaron Roth )
Doctoral student Georgy Noarov (jointly advised with Aaron Roth )
Doctoral educatee Saeed Sharifi-Malvajerdi (jointly brash with Aaron Roth )
Doctoral student Alexander Tolbert (jointly advised with Scott Weinstein)

Alumni (reverse chronological):

Onetime Warren Center postdoc Travis Dick, Now at Google Enquiry NYC.
Old Warren Center postdoc Juba Ziani, now on the Georgia Tech faculty.
Old doctoral student Hadi Elzayn , now a postdoc at Stanford
Former doctoral student Seth Neel, now on the Harvard Business School faculty
Former doctoral educatee Shahin Jabbari, now on the Drexel faculty
Former Warren Centre postdoc Jieming Mao, now at Google Research NYC
Former Warren Heart postdoc Bo Waggoner, now on the Academy of Colorado faculty
One-time Warren Eye postdoc Jamie Morgenstern, now on the University of Washington faculty
One-time doctoral student Steven Wu, now on the CMU faculty
Former doctoral student Hoda Heidari, at present on the CMU faculty
Erstwhile doctoral pupil Ryan Rogers, at present at LinkedIn
Former Warren Eye postdoc Grigory Yaroslavtsev, now on the George Bricklayer Academy faculty
Quondam doctoral student Lili Dworkin (ABD) now at Facebook
Former doctoral student Kareem Amin, now at Google Research NYC
Former research scientist Stephen Judd
One-time doctoral educatee Mickey Brautbar, now at Shipt
Erstwhile postdoc Jake Abernethy, at present on the Georgia Tech kinesthesia
Former postdoc Karthik Sridharan, now on the Cornell faculty
Sometime postdoc Kris Iyer, now on the Cornell kinesthesia
Former MD/PhD student Renuka Nayak, now on the UCSF faculty
Old doctoral student Tanmoy Chakraborty, now at Facebook
Former postdoc Umar Syed, now at Google Enquiry NYC
Quondam doctoral student Jinsong Tan, now at Square
Old postdoc Eugene Vorobeychik, now on the Washington Academy faculty
Former postdoc Giro Cavallo, now at Yahoo! NYC
Sometime doctoral pupil Jenn Wortman Vaughan, now at Microsoft Research NYC
Former postdoc Eyal Even-Dar, now at Concluding State of israel
Former doctoral pupil Sid Suri, at present at Microsoft Inquiry NYC
Former postdoc Sham Kakade, now on the Harvard faculty
Former postdoc Ryan Porter
Sometime postdoc Luis Ortiz, now on the University of Michigan-Dearborn CS kinesthesia
Former postdoc John Langford, at present at Microsoft Research NYC

Education AND TUTORIAL MATERIAL

Teaching Leap 2022: CIS 435/523, Ethical Algorithm Design (new form, based on pilots of previous years).
Teaching Autumn 2021: CIS 625, Theory of Machine Learning.
Web folio for the undergraduate course Networked Life (NETS 112), Autumn 2019 and a condensed online video version.
(See also the Fall 2018, Autumn 2017, Fall 2016, Fall 2015, Autumn 2014, Fall 2013, Fall 2012, Autumn 2011 (hosted at Lore), Leap 2010, Spring 2009, Spring 2008, Spring 2007, Spring 2006, Bound 2005, and Spring 2004 offerings.)
Web page for MKSE 150: Marketplace and Social Systems on the Internet, Jump 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 2018: Computational Learning Theory. Here is the Spring 2016 version, 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 folio for CIS 620, Fall 2006: Seminar on Sponsored Search.
Web page for the graduate seminar CIS 700/04: Advanced Topics in Car Learning (Fall 2004).
Web page for CIS 700/04: Advanced Topics in Machine Learning (Fall 2003).
Web page for a class on Computational Game Theory (Spring 2003). This was a articulation form between CIS and Wharton (listed as CIS 620 and Wharton OPIM 952).
Course spider web page for CIS 620: Avant-garde 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 Bug 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 manufactures related to my work, or in which I am quoted. (Some links are behind paywalls or are unfortunately at present expressionless.)

Science News article on AI and ideals, Feb 2022.
Interview with Clubic related to AWS ML Elevation (en Francais), June 2021.
Actuia article related to AWS ML Summit (en Francais), May 2021.
Press release on election to National Academy of Sciences and an article in Penn Today, Apr 2021.
"Who Should Stop Unethical AI?", The New Yorker [PDF version] February 2021, and a follow-upward commodity in Psychology Today, April 2021.
Penn Gazette interview on "The Ethical Algorithm", November 2020.
Series of manufactures on bias in AI in Quartz, March 2020.
NPR Marketplace on algorithmic trading and coronavirus fears, March 2020.
Ipse Dixit podcast on "The Ethical Algorithm", March 2020.
WHYY's The Pulse piece on "Can Algorithms Help Judges Make Fair Decisions?", February 2020.
Tech Nation interview with Moira Gunn on "The Ethical Algorithm", January 2020.
Interview with Aaron Roth about "The Ethical Algorithm" in SINC (Spanish), January 2020.
Philadelphia Inquirer article about confront scanning at PHL, January 2020.
Fintech Beat podcast with Chris Brummer on "The Upstanding Algorithm", Jan 2020.
Review of "The Ethical Algorithm" in Nature, January 2020.
Discussion of "The Upstanding Algorithm" at Keystone Strategy NYC, aired on CSPAN's Book TV, Dec 2019.
Word of "The Ethical Algorithm" on Beyond50 Radio, December 2019.
"The Ethical Algorithm" on Talks at Google, Dec 2019.
Steptoe CyberLaw podcast on "The Upstanding Algorithm", December 2019.
Podcast on "The Upstanding Algorithm" for Carnegie Council, Dec 2019.
Podcast on "The Ethical Algorithm" on Cognition@Wharton, Dec 2019.
Podcast of Seattle Town Hall talk on "The Upstanding Algorithm", moderated by Eric Horvitz, Nov 2019.
Interview almost "The Ethical Algorithm" on WHYY'south Radio Times (at 32 minute mark), November 2019.
Opinion piece adapted from themes in "The Ethical Algorithm" in Scientific American, November 2019.
Excerpt from "The Upstanding Algorithm" in Penn Today, Nov 2019.
NPR Market place Morn Study interview on "The Ethical Algorithm", October 2019.
Very brief informational article on deepfakes in Christian Science Monitor, October 2019.
Knowledge@Wharton article on the market for consumer information and related privacy concerns, October 2019.
A couple of articles in Penn Today on AI, ML and "The Upstanding Algorithm" and a related podcast , September 2019.
NPR Marketplace interview on presidential tweets, market place volatility and algorithms (roughly the 2 minute mark), August 2019.
Knowledge@Wharton commodity on information privacy, anonymity, and re-identification, August 2019.
WSJ commodity on Wall Street and academia, May 2019.
Bloomberg commodity on machine learning at Morgan Stanley, April 2019.
Fast Company article by Kartik Hosanagar on an algorithmic neb of rights, March 2019.
Bloomberg commodity about shutdown of the legendary Prediction Company, September 2018.
Bloomberg article about joining Morgan Stanley, June 2018.
NYT article on the European union's GDPR, May 2018.
Penn News commodity on fairness gerrymandering, Feb 2018.
NPR Market place interview on algorithmic trading and market volatility, February 2018.
"Information Skeptic" podcast with Kyle Polich on machine learning, computational complication, game theory, trading, fairness etc. November 2017.
WSJ article on financial markets counterterrorism. October 2017.
Regulatory Review article on fairness in machine learning. October 2017.
Axios commodity on "intimiate" data and machine learning, September 2017.
Interview on Fairness in Machine Learning. Aired on Sirius XM Aqueduct 111, Business Radio Powered by The Wharton School, Baronial 2017.
Pasatiempo Magazine (Santa Fe New Mexican) article almost SFI lecture on car learning and social norms, April 2017.
CBS Sun Morn segment on "Luck", September 2016.
Bloomberg news article on car 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, January-June 2016.
MIT Technology Review article on Cloverpop, September 2014.
Bloomberg News commodity 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 sound on Coursera, online teaching, and Penn, October 2012
Australian radio programme "Hereafter 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 Honour, CACM June 2011.
Profile and lecture overview, Christ'southward College Pieces, Lent Term 2011.
Fiscal Times article on motorcar learning and engineering science in trading, March 2011,
Wired Mag article on algorithmic trading, January 2011, and some more extensive remarks and i-twelvemonth follow-upwards on the writer's weblog.
Science News article on lite speed propagation delays in trading, October 2010
Economist commodity on wink crash autopsy, October 2010
WSJ online postal service on HFT research, September 2010
Give-and-take of behavioral social network experiments in Peter Miller's "The Smart Swarm" (Chapter iii, page 139 frontwards)
Atlantic article on HFT "crop circles", August 2010
Nature News article on "distributed thinking", August 2010
Wall Street Journal article on motorcar learning in quant trading, July 2010 and a related interview on CNBC
New Scientist commodity on "Why Facebook friends are worth keeping", July 2010; here is a costless reproduction
Philadelphia Business concern Periodical commodity 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 Merchandise magazine article natural language processing for algorithmic trading, September 2007
Bloomberg Markets mag article on AI on Wall Street, June 2007
SIAM News article on behavioral graph coloring, Nov 2006
Philadelphia Inquirer article on network science and NSA link analysis, May 2006
Chicago Tribune article on privacy in blogs and social networks, Nov 2005
Chronicle of Higher Instruction commodity on Facebook and social networks, May 2004
Star-Ledger commodity on the demise of AT&T Labs, March 2004
Business Week Online commodity on technology in NASDAQ and NYSE, September 2003
Philadelphia Inquirer commodity 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 [Comprehend]
Tornado Insider commodity on biometric security, January 2002
Sound of COMNET panel "Staving Off Denial-of-Service Attacks and Detecting Malicious Code"
Tornado Insider article on tongue engineering science, September 2001
Tornado Insider commodity on robotics, July 2001
Il Sole 24 Ore profile, June 2001 [English Translation]
Corriere Della Sera profile, May 2001 [English language Translation]
Associated Printing article on software robots, February 2001
New York Times commodity on TAC, August 2000
New York Times on Cobot, February 2000
TIME Digital Magazine (now Fourth dimension On) on Cobot, May 2000
Washington Postal service article on Cobot, Dec 2000
New York Times article on boosting, Baronial 1999

PUBLICATIONS:BOOKS

[PHOTO]

The Computational Complication of Machine Learning. This revision of my doctoral dissertation was published by the MIT Printing as part of the ACM Doctoral Dissertation Award Serial. As it is now out of print, I am making it available for downloading below.
[PDF]

PUBLICATIONS: RESEARCH Manufactures

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

Acronyms for conferences and journals include: AAAI: Almanac National Conference on Artificial Intelligence; AISTATS: International Conference on Bogus Intelligence and Statistics; ALT: Algorithmic Learning Theory; Colt: Annual Conference on Computational Learning Theory; EC: ACM Conference on Economics and Computation; FAccT: ACM Conference on Fairness, Accountability and Transparency (formerly FAT* and FATML); FOCS: IEEE Foundations of Reckoner Science; HCOMP: AAAI Conference on Human Computation and Crowdsourcing; ICCV: International Conference on Computer Vision; ICML: International Conference on Machine Learning; IJCAI: International Joint Conference on Artificial Intelligence; ITCS: Innovations in Theoretical Computer Science; NIPS/NeurIPS: Neural Information Processing Systems; PNAS: Proceedings of the National Academy of Science; SODA: ACM Symposium on Detached Algorithms; STOC: ACM Symposium on the Theory of Computation; UAI: Annual Briefing on Uncertainty in Artificial Intelligence; WINE: Workshop on Internet and Network Economics.

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

An Algorithmic Framework for Bias Bounties. With I. Globus-Harris and A. Roth. FAccT 2022.
[arXiv version]
Multiaccurate Proxies for Downstream Fairness. With E. Diana, W. Gill, K. Kenthapadi, A. Roth, and S. Sharifi-Malvajerdi. FAccT 2022.
[arXiv version]
Mixed Differential Privacy in Reckoner Vision. With A. Golatkar, A. Achille, Y. Wang, A. Roth, and Due south.Soatto. ICCV 2022.
[arXiv version]
Differentially Private Query Release Through Adaptive Projection. With S. Aydore, W. Brownish, 1000. Kenthapadi, L. Melis, A. Roth and A. Siva. ICML 2021.
[arXiv version] [github repo]
Algorithms and Learning for Fair Portfolio Pattern. With E. Diana, T. Dick, H. Elzayn, A. Roth, Z. Schutzman, S. Sharifi-Malvajerdi, and J. Ziani. ACM EC 2021.
[arXiv version]
Lexicographically Fair Learning: Algorithms and Generalization. With E. Diana, W. Gill, I. Globus-Harris, A. Roth and S. Sharifi-Malvajerdi. Foundations of Responsible Computing (FORC), 2021.
[arXiv version]
An Algorithmic Framework for Fairness Elicitation. With C. Jung, Southward. Neel, A. Roth, L. Stapleton, and South. Wu. Foundations of Responsible Computing (FORC), 2021.
[arXiv version]
Minimax Grouping Fairness: Algorithms and Experiments. With E. Diana, Westward. Gill, K. Kenthapadi, and A. Roth. AAAI/ACM Conference on AI, Ideals, and Society (AIES), 2021.
[arXiv version] [github repo]
Optimal, True and Private Securities Lending. With East. Diana, S. Neel, and A. Roth. ACM International Briefing on AI in Finance, 2020.
[arXiv version]
Differentially Individual Call Auctions and Market Bear on. With Due east. Diana, H. Elzayn, A. Roth, S. Sharifi-Malvajerdi, and J. Ziani. ACM EC 2020.
[arXiv version] [EC version] [EC talk]
Upstanding Algorithm Design Should Guide Engineering science Regulation. With A. Roth. Brookings Institution policy briefing, 2020.
[Brookings link]
Average Individual Fairness: Algorithms, Generalization and Experiments. With A. Roth and S. Sharifi-Malvajerdi. NeurIPS 2019.
[arXiv version]
Equilibrium Label for Data Acquisition Games. With H. Elzayn, J. Dong, S. Jabbari, and Z. Schutzman. IJCAI 2019.
[PDF]
Network Formation under Random Assail and Probabilistic Spread. With Y. Chen, S. Jabbari, S. Khanna, and J. Morgenstern. IJCAI 2019.
[arXiv version]
Differentially Private Fair Learning. With 1000. Jagielski, J. Mao, A. Oprea, A. Roth, Due south. Sharifi-Malvajerdi, and J. Ullman. ICML 2019.
[arXiv version]
Off-white Algorithms for Learning in Resource allotment Problems. With H. Elzayn, S. Jabbari, C. Jung, S. Neel, A. Roth, and Z. Schutzman. ACM FAT* 2019.
[arXiv version]
An Empirical Study of Rich Subgroup Fairness for Motorcar Learning. With S. Neel, A. Roth, and S. Wu. ACM FAT* 2019.
[arXiv version] [github repo]
Online Learning with an Unknown Fairness Metric. With Due south. Gillen, C. Jung and A. Roth. NeurIPS 2018.
[arXiv version]
Fairness in Criminal Justice Risk Assessments: The State of the Art. With R. Berk, H. Heidari, Southward. Jabbari, and A. Roth. Sociological Methods and Enquiry, July 2018.
[arXiv version] [SMR version]
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness. With Due south. Neel, A. Roth, and South. Wu. ICML 2018.
[arXiv version] [github repo] [brusque video] [tcs+ talk video]
Data Intimacy, Machine Learning, and Consumer Privacy. Penn Law CTIC whitepaper, May 2018.
[PDF]
Fair Algorithms for Infinite and Contextual Bandits. With Chiliad. Joseph, J. Morgenstern, S. Neel, and A. Roth. AAAI Briefing on AI, Ethics, and Social club, 2018. (Earlier version appeared in FATML, 2017.)
[arXiv version] [AIES version]
A Convex Framework for Fair Regression. With R. Berk, H. Heidari, South. Jabbari, Thousand. Joseph, J. Morgenstern, S. Neel, and A. Roth. FATML 2017.
[arXiv version] [FATML version]
Meritocratic Fairness for Cross-Population Selection. With A. Roth and South. Wu. ICML 2017.
[PDF]
Fairness in Reinforcement Learning. With S. Jabbari, M. Joseph, J. Morgenstern, and A. Roth. ICML 2017.
[PDF]
Predicting with Distributions. With Southward. Wu. COLT 2017.
[COLT version] [arXiv version]
Fairness Incentives for Myopic Agents. With Southward. Kannan, J. Morgenstern, M. Pai, A. Roth, R. Vorhra, and S. Wu. ACM EC 2017.
[EC version] [arXiv version]
Mathematical Foundations for Social Computing. With Y. Chen, A. Ghosh, T. Roughgarden, and J. Wortman Vaughan. CACM, December 2016.
[PDF]
Fairness in Learning: Classic and Contextual Bandits. With M. Joseph, J. Morgenstern, and A. Roth. NIPS 2016.
[NIPS version] [arXiv version]
Strategic Network Formation with Assail and Immunization. With S. Goyal, S. Jabbari, S. Khanna, and J. Morgenstern. Vino 2016.
[arXiv version]
Tight Policy Regret Bounds for Improving and Decaying Bandits. With H. Heidari and A. Roth. IJCAI 2016.
[PDF]
Private Algorithms for the Protected in Social Network Search. With A. Roth, S. Wu, and G. Yaroslavtsev. PNAS, Jan 2016.
[PNAS version] [arXiv version]
Robust Mediators in Big Games. With M. Pai, R. Rogers, A. Roth, and J. Ullman. (Subsumes and expands "Machinery 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. Vino 2015.
[PDF] [arXiv version]
From "In" to "Over": Behavioral Experiments on Whole-Network Ciphering. With 50. Dworkin. HCOMP 2015.
[PDF]
Online Learning and Profit Maximization from Revealed Preferences. With K. Amin, R. Cummings, L.Dworkin, and A. Roth. AAAI 2015.
[AAAI version] [arXiv version]
Competitive Contagion in Networks. With H. Heidari and S. Goyal. To announced in Games and Economic Beliefs. (This paper is an expanded version of the Goyal-Kearns STOC 2012 newspaper, and contains a number of new results.)
[PDF]
A Computational Written report of Feasible Repackings in the FCC Incentive Auctions. With 50.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 Awarding to Trading. With 50.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 Contamination. With M. Draief and H. Heidari. AAAI 2014.
[PDF]
Efficient Inference for Circuitous Queries on Complex Distributions. With Fifty. Dworkin and L. Xia. AISTATS 2014.
[PDF]
Marginals-to-Models Reducibility. With T. Roughgarden. NIPS 2013.
[PDF]
Auto Learning for Market Microstructure and High Frequency Trading. With Y. Nevmyvaka. Loftier Frequency Trading - New Realities for Traders, Markets and Regulators , M. O'Hara, Thousand. Lopez de Prado, D. Easley, editors. Risk Books, 2013.
[PDF] [publisher link]
Stress-Induced Changes in Cistron Interactions in Human Cells. With R. Nayak, Due west. Bernal, J. Lee, and V. Cheung. Nucleic Acids Inquiry, 2013, 1-15.
[PDF]
Depth-Workload Tradeoffs for Workforce System. With H. Heidari. HCOMP 2013.
[PDF]
Large-Scale Brigand Problems and KWIK Learning. With J. Abernethy, One thousand. 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 G. 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 Contamination 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 Scientific discipline, 2012.
[PDF]
Learning and Predicting Dynamic Behavior with Graphical Multiagent Models. With Q. Duong, 1000. Wellman, and South. Singh. AAMAS 2012.
[PDF]
Behavioral Conflict and Fairness in Social Networks. With S. Judd and E. Vorobeychik. Vino 2011.
[PDF]
A Clustering Coefficient Network Germination Game. With Chiliad. Brautbar. Symposium on Algorithmic Game Theory (SAGT), 2011.
[PDF]
Graphical Models for Bandit Problems. With 1000. Amin and U. Syed. UAI 2011.
[PDF]
Bandits, Query Learning, and the Haystack Dimension. With Yard. Amin and U. Syed. COLT 2011. (K. Amin, Best Pupil Presentation at NY Academy of Sciences ML workshop)
[PDF]
Marketplace Making and Mean Reversion. With T. Chakraborty. ACM EC 2011.
[PDF]
Designing a Digital Future: Federally Funded Research and Development in Networking and It. PCAST Working Group. Report to the President and Congress, Dec 2010.
[PDF] [Related Textile]
Empirical Limitations on High Frequency Trading Profitability. With A. Kulesza and Y. Nevmyvaka. Journal of Trading, Fall 2010. (JOT All-time 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, Baronial 2010.
[PDF] [PNAS link]
Private and 3rd-Political party Randomization in Gamble-Sensitive Equilibrium Concepts. With Thou. 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 Big Networks. With Grand. Brautbar. Innovations in Theoretical Information 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.
[Spider web Link] [PDF] [Cover Paradigm]
Censored Exploration and the Nighttime Pool Problem. With Chiliad. Ganchev, Y. Nevmyvaka, J. Wortman. UAI 2009. Periodical version in CACM, May 2010. (UAI Best Student Paper Laurels, G. 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, Jan 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 Commonage Behavior. With J. Wortman. COLT 2008.
[PDF]
Behavioral Experiments in Networked Merchandise. With South. Judd. ACM EC 2008.
[PDF]
Graphical Games. In Algorithmic Game Theory, Due north. Nisan, T. Roughgarden, E. Tardos and Five. Vazirani, editors, Cambridge University Press, September, 2007.
[PDF]
Sponsored Search with Contexts. With E. Fifty-fifty-Dar and J. Wortman. Vino 2007. The following longer version appeared in the Tertiary Workshop on Sponsored Search Auctions, Www 2007.
[PDF]
Empirical Price Modeling for Sponsored Search. With M. 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 East. 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 Boilerplate. With E. Fifty-fifty-Dar, Y. Mansour, and J. Wortman. COLT 2007. Periodical version in Car Learning Journal, book 71, 2008. (J. Wortman, Colt Best Student Newspaper Award)
[COLT Version] [MLJ Version]
A Small World Threshold for Economic Network Formation. With E. Even-Dar. NIPS 2006.
[PDF]
An Experimental Written report of the Coloring Trouble on Man Subject Networks. With S. Suri and North. Montfort. Science 313(5788), August 2006, pp. 824-827.
[Abstruse] [Full Newspaper] [PDF]
Networks Preserving Evolutionary Stability and the Power of Randomization. With S. Suri. ACM Briefing on Electronic Commerce (EC), 2006.
[PDF]
(In)Stability Properties of Limit Order Dynamics. With Eastward. 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 Eastward. 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]
Economic science, Computer Science, and Policy.
Bug in Science and Applied science, 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 South. Kakade. COLT 2005.
[PDF]
Learning from Data of Variable Quality. With Thou. Crammer and J. Wortman. NIPS 2005.
[PDF]
Economic Properties of Social Networks. With S. Kakade, Fifty. Ortiz, R. Pemantle, and S. Suri. Proceedings of NIPS 2004.
[PDF]
Graphical Economics. With S. Kakade and L. Ortiz. Proceedings of Filly 2004.
[PDF]
Competitive Algorithms for VWAP and Limit Guild Trading. With S. Kakade, Y. Mansour and 50. Ortiz. Proceedings of the ACM Conference on Electronic Commerce (EC), 2004.
[PDF]
Algorithms for Interdependent Security Games. With Fifty. 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 Fifty. Ortiz. IEEE Intelligent Systems, Nov/Dec 2003.
IEEE version [PDF] Long version [PDF]
Exploration in Metric State Spaces. With Southward. Kakade and J. Langford. ICML 2003.
[PDF]
Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System. With Due south. Singh, D. Litman, Thousand. Walker. Journal of Artificial Intelligence Enquiry, 2002.
[PDF]
Nash Propagation for Loopy Graphical Games. With L. Ortiz. Proceedings of NIPS 2002.
[PDF]
Efficient Nash Ciphering in Large Population Games with Divisional Influence. With Y. Mansour. Proceedings of UAI 2002.
[PDF]
A Annotation on the Representational Incompatabilty of Function Approximation and Factored Dynamics. With Due east. Allender, Due south. Arora, C. Moore, A. Russell. Proceedings of NIPS 2002.
[PDF]
CobotDS: A Spoken Dialogue Organization for Chat. With C. Isbell, S. Singh, D. Litman, J. Howe. Proceedings of AAAI 2002.
[PDF]
An Efficient Verbal Algorithm for Singly Connected Graphical Games. With M. Littman, S. Singh. 2001. NIPS 2001.
[PDF]

Note: The main result of the newspaper in a higher place --- an efficient algorithm claimed to notice a unmarried 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 exist found here. The problem of efficiently computing an exact Nash equilibrium in trees remains open (though EG&Thousand demonstrate that no 2-pass algorithm can suffice). The original polynomial-time guess Nash algorithm from the K., Littman, Singh UAI 2001 paper is unaffected by these developments, as is its NashProp generalization in the Ortiz and Grand. 2002 NIPS paper.

Graphical Models for Game Theory. With M. Littman, Due south. Singh. 2001. UAI 2001.
[PDF]
ATTac-2000: An Adaptive Democratic Bidding Amanuensis. With P. Stone, M. Littman, S. Singh. Periodical of Artificial Intelligence Enquiry . Before 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. Rock. Proceedings of Agents 2001. Winner of All-time Paper Award at the Briefing.
[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 Doubtfulness in Artificial Intelligence, Morgan Kaufmann, pages 309-316, 2000.
[PDF]
Bias-Variance Error Bounds for Temporal Difference Updates. With Southward. Singh. Proceedings of the 13th Almanac Conference on Computational Learning Theory, 2000, pages 142--147.
[PDF]
Guess Planning in Large POMDPs via Reusable Trajectories. With Y. Mansour and A. Ng. Advances in Neural Information Processing Systems 12, MIT Printing, 2000.
[PDF] [Long Version]
Testing Bug with Sub-Learning Sample Complexity. With D. Ron. Periodical of Computer and System Sciences, 61, pp. 428-456, 2000. Before 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, Southward. Singh, P. Stone. Proceedings of the 17th National Conference on Artificial Intelligence, pp. 36-41, 2000, AAAI Printing/MIT Press.
[PDF]
Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System. With Southward. Singh, D. Litman, M. Walker. Proceedings of the 17th National Briefing on Artificial Intelligence, pp. 645-651, 2000, AAAI Printing/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, Yard. Walker. Appeared in ICML 2000.
[PDF]
Reinforcement Learning for Spoken Dialogue Systems. With S. Singh, D. Litman and K. Walker. Advances in Neural Information Processing Systems 12, MIT Printing, 2000.
[PDF]
Automated Detection of Poor Speech communication Recognition at the Dialogue Level. With D. Litman and M. Walker. Proceedings of the 37th Almanac Meeting for Computational Linguistics, 1999, pages 309-316.
[PDF]
A Thin Sampling Algorithm for Near-Optimal Planning in Big Markov Decision Processes. With Y. Mansour and A. Ng. Proceedings of the Sixteenth International Joint Briefing on Artificial Intelligence Morgan Kaufmann, 1999, pages 1324--1331. Likewise appeared in a special upshot 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 South. Singh. Advances in Neural Information Processing Systems 11, The MIT Press, 1999, pages 996--1002.
[PDF]
Inference in Multilayer Networks via Big Deviation Bounds. with Fifty. Saul. Advances in Neural Information Processing Systems xi, The MIT Press, 1999, pages 260--266.
[PDF]
Big Difference Methods for Estimate Probabilistic Inference, with Rates of Convergence. With 50. 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 Doubt in Artificial Intelligence, Morgan Kaufmann, 1998, pages 304--310.
[PDF]
Near-Optimal Reinforcement Learning in Polynomial Time. With Due south. Singh. Proceedings of the 15th International Conference on Machine Learning, pp. 260-268, 1998, Morgan Kaufmann. Appeared in a special issue of the periodical Machine Learning.
[PDF]
A Fast, Bottom-Upwards Decision Tree Pruning Algorithm with Almost-Optimal Generalization. With Y. Mansour. Proceedings of the 15th International Conference on Auto 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 Incertitude 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: Contempo Developments in Conclusion Tree Consecration and the Weak Learning Framework. Abstract accompanying invited talk given at AAAI '96, Portland, Oregon, August 1996.
[PDF]
Applying the Weak Learning Framework to Empathise and Better C4.5. With T. Dietterich and Y. Mansour. Proceedings of the 13th International Briefing on Motorcar 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 Fault of Cantankerous Validation Using the Approximation and Estimation Rates, with Consequences for the Training-Test Dissever. Neural Ciphering ix(five), 1997, pages 1143--1161. Earlier version in Advances in Neural Information Processing Systems eight, The MIT Press, pages 183--189, 1996.
[PDF]
An Experimental and Theoretical Comparison of Model Choice Methods. With Y. Mansour, A. Ng, and D. Ron. Machine Learning 27(1), 1997, pages vii--50. Before 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 Divisional 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 Complication of Instruction. With S. Goldman. Journal of Estimator and Systems Sciences, 50(1), pp. twenty-31, 1995.
[PDF]
On the Learnability of Detached Distributions. With Y. Mansour, R. Rubinfeld, D. Ron, R. Schapire, and 50. Sellie. Proceedings of the 26th Almanac ACM Symposium on the Theory of Computing, pp. 273-282, 1994, ACM Press.
[PDF]
Cryptographic Primitives Based on Hard Learning Issues. With A. Blum, M. Furst, and R. Lipton. Advances in Cryptology, Lecture Notes in Computer Science, Book 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. Before version in ACM Conference on Computational Learning Theory, pp. 76-87, 1994, ACM Press.
[PDF]
The Minimal Disagreement Parity Problem every bit a Difficult Satisfiability Trouble. With J. Crawford and R. Schapire. Unpublished manuscript, 1994.
[PDF]
Weakly Learning DNF and Characterizing Statistical Query Learning Using Fourier Assay. With A. Blum, M. Furst, J. Jackson, Y. Mansour, and S. Rudich. Proceedings of the 26th Almanac ACM Symposium on the Theory of Computing, pp. 253-262, 1994, ACM Press.
[PDF]
Efficient Dissonance-Tolerant Learning from Statistical Queries. Periodical of the ACM , 45(half-dozen), 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 South. 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 Doubter Learning. With R. Schapire and L. Sellie. Auto Learning 17, pp. 115-141, 1994. Earlier version in Proceedings of the Fifth Almanac Workshop on Computational Learning Theory, pp. 341-352, 1992, ACM Press.
[PDF]
Premises on the Sample Complexity of Bayesian Learning Using Information Theory and the VC Dimension. With D. Haussler and R. Schapire. Machine Learning fourteen, pp. 83-113, 1994. Earlier version in Proceedings of the Fourth Almanac 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. Data 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 Almanac IEEE Symposium on Foundations of Computer Science, pp. 382-391, 1990, IEEE Printing.
[PDF]
Exact Identification of Read-in one case 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 Information science, pp. 193-202, 1990, IEEE Press.
[PDF]
A Polynomial-Time Algorithm for Learning k-Variable Pattern Languages from Examples. With L. Pitt. Filly 1989. (Unfortunately missing references, bib file got corrupted)
[PDF]
Cryptographic Limitations on Learning Boolean Formulae and Finite Automata. With 50. Valiant. Journal of the ACM 41(1), pp. 67-95, 1994. Earlier version in Proceedings of the 21st ACM Symposium on the Theory of Calculating, pp. 433-444, 1989, ACM Press.
[PDF]
A Full general Lower Bound on the Number of Examples Needed for Learning. With A. Ehrenfeucht, D. Haussler, and L. Valiant. Data and Computation 82(iii), 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 Calculating, pp. 267-280, 1988, ACM Press.
[PDF]
Thoughts on Hypothesis Boosting. Unpublished manuscript, 1988. Project for Ron Rivest's motorcar learning course at MIT.
[PDF]
On the Learnability of Boolean Formulae. With K. Li, L. Pitt, and Fifty. 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 50. Valiant. Periodical 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 Fifty. Valiant. Proceedings of the Fourth International Conference on Machine Learning, pp. 337-352, 1987, Morgan Kaufmann.
[PDF]