James R. Wright

Microsoft Research
7th Floor
641 Avenue of the Americas
New York, NY 10011
jrwright@microsoft.com

Research Interests

My primary research interest is in using data-driven machine learning models to predict human strategic behaviour; that is, behaviour in interactions where each participant's rewards depend partially on the actions of other participants. My long-term research agenda is to build a general theory for optimally designing algorithms for mediating interactions involving humans or other realistically bounded agents rather than idealized, perfectly rational game theoretic agents.

Education

2010–2016
Doctor of Philosophy
Dissertation: Modeling Human Behavior in Strategic Settings
ACM SIGecom Doctoral Dissertation Award (Honorable Mention)
University of British Columbia, Canada
2007–2010
Master of Science in Computer Science
Thesis: Beyond Equilibrium: Predicting Human Behaviour in Normal Form Games
University of British Columbia, Canada
1995–2000
Bachelor of Science in Computing Science
Simon Fraser University, Canada

Publications

Competitive peer-reviewed conferences

  1. Learning in the Repeated Secretary Problem.
    Daniel G. Goldstein, R. Preston McAfee, Siddarth Suri, and James R. Wright.
    ACM Conference on Economics and Computation (ACM-EC), 2017.
  2. Deep Learning for Predicting Human Strategic Behavior.
    Jason Hartford, James R. Wright, and Kevin Leyton-Brown.
    NIPS 2016: Thirtieth Annual Conference on Neural Information Processing Systems, 2016.
    Oral presentation.
  3. Level-0 Meta-Models for Predicting Human Behavior in Games.
    James R. Wright and Kevin Leyton-Brown.
    ACM Conference on Economics and Computation (ACM-EC), 2014.
  4. Behavioral Game-Theoretic Models: A Bayesian Framework For Parameter Analysis.
    James R. Wright and Kevin Leyton-Brown.
    Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), pages 921–928, 2012.
    Best student paper (runner up).
  5. Beyond Equilibrium: Predicting Human Behavior in Normal Form Games.
    James R. Wright and Kevin Leyton-Brown.
    Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI-10), pages 901–907, 2010.

Journals

  1. Predicting Human Behavior in Unrepeated, Simultaneous-Move Games.
    James R. Wright and Kevin Leyton-Brown.
    Games and Economic Behavior, Volume 106, pages 16–37, November 2017.
    (supersedes Wright & Leyton-Brown [2010, 2012])

Under review

  1. Models of Level-0 Behavior for Predicting Human Behavior in Games.
    James R. Wright and Kevin Leyton-Brown.
    Under review at Journal of Artificial Intelligence Research.
    (supersedes Wright & Leyton-Brown [2014])
  2. Incentivizing Evaluation via Limited Access to Ground Truth:
    Peer-Prediction Makes Things Worse.

    Xi Alice Gao, James R. Wright, and Kevin Leyton-Brown.
    Under review by Artificial Intelligence Journal.
    (supersedes Gao, Wright, and Leyton-Brown [2016])
  3. Learning in the Repeated Secretary Problem.
    Daniel G. Goldstein, R. Preston McAfee, Siddarth Suri, and James R. Wright.
    Under review by Management Science.
    (Full version of Goldstein et al. [2017])

Other venues

  1. Incentivizing Evaluation via Limited Access to Ground Truth:
    Peer-Prediction Makes Things Worse.

    Xi Alice Gao, James R. Wright, and Kevin Leyton-Brown.
    Workshop on Algorithmic Game Theory and Data Science at ACM Conference on Economics and Computation, 2016.
  2. Mechanical TA: Partially Automated High-Stakes Peer Grading.
    James R. Wright, Chris Thornton, Kevin Leyton-Brown.
    ACM Technical Symposium on Computer Science Education (ACM-SIGCSE), 2015.
  3. Linear Solvers for Nonlinear Games: Using Pivoting Algorithms to Find Nash Equilibria in n-Player Games.
    James R. Wright, Albert Xin Jiang, and Kevin Leyton-Brown.
    SIGecom Exchanges, volume 10, number 1, pages 9–12, 2011.

Invited Talks

INFORMS-2017
Deep Learning for Human Strategic Modeling.
At INFORMS Annual Meeting,
Houston, Texas. 2017.
CODE-2017
Bayesian Models of Learning in the Repeated Secretary Problem.
At 2017 Conference on Digital Experimentation (CODE@MIT),
Boston, Massachusetts. 2017.
EC-17
Learning in the Repeated Secretary Problem.
At ACM Conference on Economics and Computation (ACM-EC),
Boston, Massachusetts. 2017.
IFORS-2017
Deep Learning for Human Strategic Modeling.
At 21st Conference of the International Federation of Operations Research Societies,
Québec City, Québec. 2017.
Simons
Endogenous Cognitive Hierarchy.
At Simons Institute Survey Seminar,
Berkeley, California. 2015.
UBC
Guest lecture for CPSC 430.
University of British Columbia. January, 2015.
ISMP-2015
Level-0 Meta-Models for Predicting Human Behavior in Games.
At 22nd International Symposium on Mathematical Programming
Pittsburgh, Pennsylvania. 2015.
SIGCSE-15
Mechanical TA: Partially Automated High-Stakes Peer Grading.
At ACM Technical Symposium on Computer Science Education,
Kansas City, Missouri. 2015.
UBC
Guest lecture for CPSC 532L.
University of British Columbia. January, 2014.
SFI
Evaluating Set-Valued Predictions.
At Combining Information Theory and Game Theory,
Santa Fe Institute, New Mexico. 2012.
AAMAS-2012
Behavioral Game-Theoretic Models: A Bayesian Framework For Parameter Analysis.
At 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), Valencia, Spain. 2012.
GAMES-2012
Beyond Equilibrium: Predicting Human Behavior in Normal Form Games.
At 4th World Congress of the Game Theory Society (GAMES-2012), Istanbul, Turkey. 2012.
UBC
Guest lecture for PSYC 417A.
University of British Columbia. February 2012.
LANL
Beyond Equilibrium: Predicting Human Behavior in Normal Form Games.
At Design and Control of Systems of Goal-Directed Agents; From Game Theory to Game Engineering,
Los Alamos National Laboratory, New Mexico. 2010.
AAAI-10
Beyond Equilibrium: Predicting Human Behavior in Normal Form Games.
At Twenty-Fourth AAAI Conference on Artificial Intelligence,
Atlanta, Georgia. 2010.
Google
Beyond Equilibrium: Predicting Human Behavior in Normal Form Games.
At Google,
Mountain View, California. 2010.
BQGT
Beyond Equilibrium: Predicting Human Behavior in Normal Form Games.
At Behavioral and Quantitative Game Theory Conference on Future Directions,
Newport Beach, California. 2010.

Awards

2017
ACM SIGecom Doctoral Dissertation Award (Honorable Mention)
ACM Special Interest Group on E-commerce
2010–2013
University Graduate Fellowship
University of British Columbia, Canada
Declined in 2010–2012 to hold NSERC
Total value: $80,000
2010–2012
Canada Graduate Scholarship (Ph.D.)
Natural Sciences and Engineering Research Council of Canada
Total value: $105,000
2008–2009
Canada Graduate Scholarship (M.Sc.)
Natural Sciences and Engineering Research Council of Canada
Total value: $17,500
2000
Computing Science Graduation Award (for top graduating student in department)
Simon Fraser University, Canada
Total value: $600
1996 (twice)
and 1999
Honour Roll
Simon Fraser University, Canada
1996–2000
Open Scholarship
Simon Fraser University, Canada
Full tuition support
1995–1996
Taduesz Specht Memorial Scholarship in Science
Simon Fraser University, Canada
Total value: $3,000

Service

2017
Co-organizer: 2017 New York Computer Science and Economics Day.
2015–ongoing
Member: NSF PI Forum on Peer Assessment.
2014–2015
Student representative: Faculty Recruiting Committee.
2010
Volunteer: AAAI Conference on Artificial Intelligence.

Editorial Activity

2018
Program Committee, 19th ACM Conference on Economics and Computation.
2018
Reviewer, Games and Economic Behavior.
2017
Program Committee, 27th International World Wide Web Conference.
2017
Program Committee, Thirty-Second AAAI Conference on Artificial Intelligence.
2017
Program Committee, 18th ACM Conference on Economics and Computation.
2017
Reviewer, Thirty-First Annual Conference on Neural Information Processing Systems.
2017
Reviewer, Journal of Artificial Intelligence Research.
2016
Program Committee, Thirty-First AAAI Conference on Artificial Intelligence.
2016
Reviewer, Econometrica.
2016
Reviewer, Journal of Artificial Intelligence Research.
2016
Reviewer, 12th Conference on Web and Internet Economics.
2016
Reviewer, Artificial Intelligence Journal.
2016
Reviewer, Journal of Economic Behavior and Organization.
2015
Reviewer, Games and Economic Behavior.
2015
Reviewer, Thirtieth AAAI Conference on Artificial Intelligence.
2015
Reviewer, Journal of Economic Behavior and Organization.
2015
Reviewer, ACM Transactions on Economics and Computation.
2013
Reviewer, Journal of Machine Learning Research.
2012
Reviewer, Games and Economic Behavior.
2011
Reviewer, Artificial Intelligence Journal.
2011
Reviewer, International Joint Conferences on Artificial Intelligence.
2011
Reviewer, Twenty-Fifth AAAI Conference on Artificial Intelligence.
2010
Reviewer, Journal of Autonomous Agents and Multiagent Systems.
2009
Reviewer, ACM Conference on Electronic Commerce.
2009
External reviewer, International Joint Conferences on Artificial Intelligence.

Research Employment

2018–
Assistant Professsor
University of Alberta, Edmonton, Canada
2016–2018
Postdoctoral Researcher
Microsoft Research, New York City, New York
2015
Visiting Graduate Student
One of 16 graduate students selected to participate in the Economics and Computation Program, along with 45 faculty.
Simons Institute, University of California, Berkeley, California
2008–2016
Graduate Researcher
Advisor: Kevin Leyton-Brown
University of British Columbia, Vancouver, Canada
2000
Undergraduate Research Assistant
Supervisor: Binay Bhattacharya
Simon Fraser University, Burnaby, Canada
1998
Undergraduate Research Assistant
Supervisors: Jim Delgrande and Arvind Gupta
Simon Fraser University, Burnaby, Canada

Teaching

My duties as an instructional assistant for the various massively open online courses listed below included constructing new content (problem sets and exams), cross-checking new video comment for slide typos and misstatements, and monitoring and responding to student questions in online forums.

As an instructional assistant for Computers and Society, I led the design and implementation effort of the Mechanical TA peer grading system. I also constructed exams, and assisted with curriculum development.

As a teaching assistant for Multiagent Systems, I constructed quizzes, exams, and assignments, and assisted in the day-to-day operation of the class.

2014
Instructional Assistant, Coursera/University of British Columbia
Game Theory II (Massively Open Online Course), Kevin Leyton-Brown.
2014
Instructional Assistant, Coursera/University of British Columbia
Game Theory (Massively Open Online Course), Kevin Leyton-Brown.
2014
Teaching Assistant, University of British Columbia
Multiagent Systems (graduates), Kevin Leyton-Brown.
2014
Instructional Assistant, University of British Columbia
Computers and Society (advanced undergraduates), Kevin Leyton-Brown.
2013
Instructional Assistant, University of British Columbia
Game Theory II (Massively Open Online Course), Kevin Leyton-Brown.
2013 (twice)
Instructional Assistant, Coursera/University of British Columbia
Game Theory (Massively Open Online Course), Kevin Leyton-Brown.
2013
Teaching Assistant, University of British Columbia
Multiagent Systems (graduates), Kevin Leyton-Brown.
2013
Instructional Assistant, University of British Columbia
Computers and Society (advanced undergraduates), Kevin Leyton-Brown.
2009
Teaching Assistant, University of British Columbia
Multiagent Systems (graduates), Kevin Leyton-Brown.
2008
Teaching Assistant, University of British Columbia
Computers and Society (advanced undergraduates), Kurt Eiselt.
2007
Teaching Assistant, University of British Columbia
Advanced Software Engineering (advanced undergraduates), Eric Wohlstadter.

Last update: Mar 29/2018