Special Topics in Business Analytics: Online Learning and Optimization

Overview: This course studies how to make sequential decisions under uncertainty. We will develop online-learning and online-optimization methods with provable performance guarantees, study full-information and bandit feedback, and connect these ideas to inventory control and dynamic pricing.

Learning Objectives: Students will learn to formulate sequential decision problems, analyze algorithms such as Hedge, online gradient methods, UCB, and EXP3, prove regret guarantees, and adapt these tools to new problems.

Requirements: Three homework assignments and a final project consisting of a midterm proposal, a written report, and a final presentation.

Grading:

• Homework: 30% (three assignments, 10% each)
• Project: 70% (written report: 30%; final presentation: 40%)

Prerequisites: Familiarity with probability, calculus, linear algebra, optimization, and algorithm analysis. Prior exposure to machine learning is helpful but not required.

Related Materials and Courses: There is no required textbook. The following resources provide useful background and complementary perspectives.

Books:

• Introduction to Online Convex Optimization by Elad Hazan.
• Prediction, Learning, and Games by Nicolò Cesa-Bianchi and Gábor Lugosi.
• Bandit Algorithms by Tor Lattimore and Csaba Szepesvári.
• Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto.
• Reinforcement Learning: Theory and Algorithms by Alekh Agarwal, Nan Jiang, Sham Kakade, and Wen Sun.

Notes:

• Introduction to Online Optimization by Sébastien Bubeck.
• A Modern Introduction to Online Learning by Francesco Orabona.
• Online Learning and Online Convex Optimization by Shai Shalev-Shwartz.
• Statistical Reinforcement Learning and Decision Making by Dylan Foster and Sasha Rakhlin.
• Reinforcement Learning: A Comprehensive Overview by Kevin P. Murphy.

Related Courses:

• Introduction to Online Optimization/Learning (Spring 2026) by Haipeng Luo.
• Reinforcement Learning (Spring 2026) by Chen-Yu Wei.
• Foundations of Reinforcement Learning (Fall 2025) by Chi Jin.
• Advanced Optimization (Fall 2025) by Peng Zhao.
• Bandits and Reinforcement Learning (Fall 2017) by Alekh Agarwal and Alex Slivkins.