MIT EECS, 6.853 Algorithmic Game Theory and Data Science
- Online learning, online convex optimization, minimax theorem from no-regret learning. [Lecture 3] [Lecture 4]
- Online learning and general games: correlated equilibrium via no-regret, quality of no-regret outcomes [Lecture 7] [Lecture 8]
- Intro to Statistical Learning Theory: Rademacher complexity, Growth number [Lecture 13] [Lecture 14]
- Statistical Learning Theory and Mechanism Design: learning optimal auctions from samples [Lecture 15] [Lecture 16]
- Estimation in Games: learning value CDFs from bids in an auction [Lecture 20]
- Revenue inference and A/B testing in auctions [Lecture 21]
- Welfare guarantees from data [Lecture 22a]
- Online learning of mechanisms [Lecture 22b]
The remainder of the lectures of the course can be found here: [AGT and Data Science Lectures]
Cornell mini-course: Econometric Theory for Games
- Part I: Intro to Econometrics and Econometrics of Bayesian Games [Part I]
- Part II: Complete Information Games and Set Inference [Part II]
- Part III: Dynamic Games and Auctions [Part II]
Learning and Mechanism Design Survey
- Learning and Mechanism Design [Presentation]