Fall 2020 (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 class to discuss course logistics: Thu 1 Oct 2020)

Place: Online on Microsoft Teams
To join meetings for this course, click here.
To join the Team for this course (for announcements, discussions and course material), click here.

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 techniques in sequential learning and optimization making under uncertainty. We will explore several frameworks and algorithms for online and reinforcement learning, aiming to develop a rigorous understanding. We will also look at interesting applications of these techniques, such as portfolio optimization (finance), sequential data compression (information theory), etc.

Contents: (subject to change) Online classification; Regret Minimization; Learning with experts; Online convex optimization; Stochastic games, Blackwell approachability; Multi-armed bandits, Reinforcement learning

Prerequisites: A basic course in probability or stochastic processes. Exposure to convexity (convex geometry, convex analysis or convex optimization) will be helpful but is not absolutely necessary. Contact the instructor for clarifications.


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