Course No.: EECS 598-006
Credit Hours: 3
Instructor: Jacob Abernethy
This course will focus on the problem of prediction, learning, and decision making, yet the underlying theme will involve game playing, betting and minimax analysis. We will explore several classic algorithms -- e.g. Boosting, Multiplicative Weights, the Perceptron -- through this game-theoretic lens. We will begin by introducing the classical Weighted Majority Algorithm, and more broadly the problem of adversarial online learning and regret minimization, and this will launch us into topics such as von Neumanns Minimax Theorem, multi-armed bandit problems, Blackwell Approachability, calibrated forecasting, and proper scoring rules. I intend to spend some time on applications to finance, like repeated gambling, universal portfolio selection, and option pricing.
There will be no specific prerequisites for the course, but the material is going to be about 80% "theory" and thus a strong mathematical background will be important. We shall rely heavily on techniques from calculus, probability, and convex analysis, but most tools will be presented in lecture. There will be a small number of problem sets, and the final project for the course will consist of the option to do independent research or to give a literature review presentation to the class. [Full Story]