Topics in Algorithmic Game Theory

Graduate / Professional

The course focuses on algorithms and the complexity of equilibrium computation as well as its connection with learning theory and optimization. As many recent machine learning approaches have moved from an optimization perspective to an “equilibration” perspective, where a good model is framed as the equilibrium of a game. The intersection of game theory, learning theory, and optimization is becoming increasingly relevant. The goal of the course is to cover the fundamentals and bring students to the frontier of this active research area. Prerequisites: A course in algorithms (CPSC 365 or 366) and a course in probability theory (MATH/S&DS 241). A course in algorithmic game theory (CPSC 455/555) is helpful but not required. HTBA