Prerequisite: IE 621 or IE 611 or EE 325 or EE 601 or CS 723 or IE 605 or DS 203 or SC 629 or EE 734
Description:
Brief introduction to batch learning methods and algorithms, Introduction to online learning methods: adversarial and stochastic settings, Online learning with expert feedback, bandit feedback, partial monitoring: algorithms and their analysis, Pure exploration algorithms, Introduction to reinforcement learning and connection to bandits
References:
T. Lattimore and C. Szepesvari, ``Bandit Algorithms,302222302222 Cambridge Press, 20192) S. Shalev-Shwartz and S. Ben-David, ``Understanding Machine Learning: From Theory to Algorithms,``Cambridge University Press, 20143) S. Shalev-Shwartz, Foundation and Trends in machine learning, ``Online Learning and Online Convex Optimization,``NOW publisher, 24) S. Bubeck and N. Cesa-Bianchi, ``Regret Analysis of Stochastic and Nonstochastic Multi-armedBandit Problems,`` Foundation and Trends in machine learning, NOW publisher, 25) N. Cesa-Bianchi and G. Lugosi, ``Prediction, Learning, and Games, Cambridge University Press, 2006