Online Optimization and Learning in Games (Fall 2026)

Online Optimization and Learning in Games (Fall 2026)

Course Information

Overview

This course studies how algorithms learn from repeated interaction with possibly changing or strategic environments, and their applications in optimization, games, forecasting, and mechanism design. We begin with simple online learning problems, and gradually build toward applications in equilibrium computation, calibrated forecasting, fairness auditing, downstream decision-making, strategic manipulation, algorithmic pricing, and Bayesian persuasion. The goal is to understand how to design learning algorithms with guarantees of stability, reliability, and incentive compatibility.

Tentative syllabus

Prerequisites

Probability, linear algebra, calculus, convex analysis, mathematical maturity.

Grading (tentative)