Incentives and Machine Learning

CSC 482A/581A, Spring 2026

Lectures: Tuesdays, Wednesdays, and Fridays 11:30am - 12:20pm, DSB C108
Instructor: Nishant Mehta (n<lastname>@uvic.ca)
TA: Ali Mortazavi (<firstname>themorty@gmail.com)
Office hours:
    Nishant: ECS 608, Tuesdays, 3pm - 4:30pm or by appointment
    Ali: ECS 668, Thursdays, 3pm - 4pm or by appointment

There is no required textbook for this course, but the following are the most related books:

Official course outlines: CSC 482A    CSC 581A

Schedule
Info about readings      Info about presentations of research papers      Info about the project

What is this course about?

In many real-world problems, we wish for a system to obtain information from self-interested participants (agents) and then decide an outcome that maximizes some notion of utility. Auctions and machine learning algorithms are just a few examples of such systems. The agents being self-interested poses a key challenge: the mapping from the agents' reported information to the outcome (which could involve giving partipants some goods, payments, or both) must be carefully selected in order to incentivize partipants to report their information truthfully. Mechanism design, a subfield of algorithmic game theory, is about the design of such systems. Designing a system can be thought of as designing the rules of the game. How can we design a mechanism to achieve favorable outcomes? What can go wrong if a mechanism isn't designed well?

A major theme of this course is the interaction between economics and computation. In particular, we will look at connections between learning algorithms and mechanism design. Some of these connections include: how to use learning algorithms to approximate various notions of equilibria (essentially, stable strategies) of games; how to learn classifiers in the presence of strategic agents that provide the data points; how to sequentially learn from self-interested experts while simultaneously incentivizing the experts to truthfully report their information.

Course structure

This course is an advanced topics course, intended for research-focused graduate students as well as advanced undergraduate students. In the first major part of the course of the course, the instructor will give lectures on foundational material in mechanism design and online learning. This foundation will set the stage for us to focus on research papers. In the second major part of the course, in each lecture a pair of students or one student (or occasionally the instructor, depending on enrollment) will present a research paper to the class and lead an in-class discussion of that paper.

In the schedule below:

Schedule
Date Topics and Readings Additional Resources Reading Questions Presenter
1/6 Introduction
📖 (Twenty): Lecture 1
1/7 Normal-form games, Equilibria
📖 (MAS): Chapter 3 until the end of Section 3.3.3 (skip Section 3.1.2)
📖 (MAS): Section 3.4.3
1/9 continuation
1/13 Information elicitation, proper scoring rules
📖 Sections 1, 2, and 3 (up to the end of Section 3.1) of:
📖 Strictly Proper Scoring Rules, Prediction, and Estimation
📖 Gneiting and Raftery. JASA, 2007.
Lectures 4 and 5 lecture notes
Elicitation of Personal Probabilities and Expectations
Savage. JASA 1971. (reading guide)
1/14 Information elicitation continued
1/16 Single-item auctions, second-price auction
📖 (Twenty) Lecture 2
Lectures 6–8 lecture notes
1/20 General auctions, Vickrey-Clarke-Groves (VCG) mechanism
📖 (Twenty) Lecture 7
1/21 VCG and discussion
1/23 Single-parameter environments
Characterization of DSIC mechanisms, Myerson’s lemma
📖 (Twenty) Lecture 3
📖    Section 3.4 is optional (in-class proof will be different)
📖 (Twenty) Section 4.3 of Lecture 4
Lectures 9–10 and 11 (first part) lecture notes
1/27 continuation
1/28 Revelation principle
Congestion games, Best-response dynamics
📖 Lecture 2 from Bo Waggoner's AGT course
Lecture 11 (second part) and 12–13 lecture notes Reading Questions
(due 1/29)
1/30 Congestion games, Best-response dynamics
Potential games
📖 Lecture 3 from Bo Waggoner's AGT course
2/3 Best-response dynamics, Potential games
2/4 Online learning, Prediction with expert advice
📖 Prediction, Learning, and Games
📖    Chapter 1
📖    Chapter 2: until end of Section 2.2 (reading guide for Section 2.1)
Lectures 14–15 lecture notes Reading Questions
(due 2/5)
2/6 Regret analysis, Hedge
2/10 No-regret dynamics, Von Neumann’s minimax theorem, and MNE
📖 Game Theory, On-line Prediction and Boosting
📖 Freund and Schapire. COLT, 1996.
📖    Sections 1–3 (Section 4 is awesome + strongly recommended!)
2/11 continuation
2/13 Correlated equilibrium, Coarse corelated equilibrium, swap regret
READING BREAK
2/24 No-regret dynamics, correlated equlibrium
2/25 Prediction markets, Market scoring rule
Hanson's paper
2/27 Mechanism design without money, House allocation
Student or Prof Research Paper Presentations
3/3 Incentive-Compatible Forecasting Competitions
Witkowski, Freeman, Wortman Vaughan, Pennock, Krause.
Management Science, 2023.
3/4 No-regret and Incentive-compatible Online Learning
Freeman, Pennock, Podimata, Wortman Vaughan.
ICML, 2020.
3/6 Eliciting Informative Feedback: The Peer-Prediction Method
Miller, Resnick, Zeckhauser.
Management Science, 2005.
3/10 An Information Theoretic Framework For Designing
Information Elicitation Mechanisms That Reward Truth-telling

Kong and Schoenebeck.
Transactions on Economics and Computation 2019.
3/11 Strategic Classification
Hardt, Megiddo, Papadimitriou, Wooters.
ITCS 2016.
3/13 Alternative Microfoundations for Strategic Classification
Jagadeesan, Mendler-Dünner, Hardt.
ICML 2021.
3/17 Performative Prediction
Perdomo, Zrnic, Mendler-Dünner, Hardt.
ICML 2020.
3/18 A Market Framework for Eliciting Private Data
Waggoner, Frongillo, Abernethy.
NIPS 2015.
3/20 Selling Privacy at Auction
Ghosh and Roth.
Games and Economic Behavior 2015.
3/24 Conducting Truthful Surveys, Cheaply
Roth, Schoenebeck.
EC, 2012.
3/25 An Equivalence Between Fair Division and Wagering Mechanisms
Freeman, Witkowski, Wortman Vaughan, Pennock.
Management Science 2024.
Project Presentations
3/27 Project presentations
3/31 Project presentations
4/1 Project presentations