CS 498 GA3

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: 1 to 4 undergraduate hours. 1 to 4 graduate hours. May be repeated in the same or separate terms if topics vary.

This course builds foundational knowledge at the intersection of game theory, social choice, and machine learning theory. Students will develop both technical fluency and research intuition across three interconnected areas. Topics in algorithmic game theory and social choice include classical results such as the Prisoner?s Dilemma, Stackelberg games, Nash equilibrium, price of anarchy, fair division, and voting theory. Topics in machine learning theory will cover multi-armed bandits, learning from experts, and the strategic dimensions of learning systems. This course also explores broader themes, such as human-AI collaboration and behavioral game theory, as well as mechanism design and implications for regulation of AI systems. The course is primarily lecture-based and culminates in an extensive research or survey project. Its twin goals are to introduce students to classical results in these areas and to expose them to research in this field. Prerequisite: CS 374. For up-to-date in