Fall 2022 (Aug-Dec)

Online Prediction and Learning

Course No.: E1 245

Instructor: Aditya Gopalan, ECE 2.09, Dept. of ECE, E-mail: first-name AT iisc.ac.in

Time: TTh 11:30-13:00 (First meeting on Thu 4 Aug 2021)

Place: ECE 1.08
Class participants will need to join a Teams portal for this course (for announcements, discussions and course material), click here to join.

Course Description: The ability to make continual and accurate forecasts and decisions under uncertainty is key in many of today’s data-driven intelligent systems (think Internet recommendation engines, automated trading, resource allocation, etc.). This elective course exposes students to common approaches in sequential learning and optimization under uncertainty. We will explore several formulations and algorithms for low-regret optimization, and introduce tools and techniques for rigorous performance analysis.

Contents: Online convex optimization — Follow the leader, Follow the regularized leader, Online mirror descent, Learning with expert advice, Adversarial bandits and EXP3; Multi-armed bandits — UCB, Thompson sampling, Linear bandits, Contextual bandits.

Prerequisites: A course in probability or random processes, and basic knowledge of multivariable calculus (i.e., familiarity with gradients of functions of several variables, Taylor series). Exposure to convexity (convex geometry, convex analysis or convex optimization) will be helpful but is not absolutely necessary. Contact the instructor for clarifications.

References: The course will be based on material from the following texts:

Last updated: 12-Feb-2024, 11:46:37 IST