AI543: Foundations of Online Machine Learning – Winter 2026

Course Description

In this course, we will focus on algorithms for online learning and sequential decision-making including online convex optimization, bandits, and online reinforcement learning, examine their theoretical guarantees and applications in real-world machine learning problems such as information retrieval (advertising, recommender system, web search and ranking).

Course Information

Lectures

Tuesday & Thursday 12 - 1:50pm, Bexell Hall 412

Instructor

Huazheng Wang
Email: huazheng.wang [at] oregonstate.edu
Office: KEC 3097
Office hours: Thursday 2-4pm, KEC 3097

Prerequisites

AI 534 or CS 534.

Contact

We will use Canvas for slides and assignments, and Discord for communication. See Canvas announcements for the link to Discord channel.

Prerequisites

  • Familiar with probability, statistics, linear algebra, calculus and machine learning.

  • Python. We will use Python for programming assignments.

Schedule

Week Date Lecture Readings Notes
Week 1 1/6 Introduction to the course
1/8 Review of linear algebra, statistics and optimization
Week 2 1/13 Online Gradient Descent
1/15 Online-to-Batch Conversion HW1 posted.
Week 3 1/20 Follow the Regularized Leader
1/22 Online Learning with Expert Advice
Week 4 1/27 Stochastic Multi-Armed Bandits
1/29 Regret Lower Bounds HW1 due. HW2 posted.
Week 5 2/3 Multi-Armed Bandits and Linear Bandits
2/5 Thompson Sampling
Week 6 2/10 Generalized Linear Model, Kernel, and Neural Bandits
2/12 Bandit Convex Optimization HW2 due. HW3 posted.
Week 7 2/17 Contextual Bandits
2/19 Non-stationary Regret Minimization
Week 8 2/24 Online Learning to Rank
2/26 Combinatorial Bandits Learning HW3 due. HW4 posted.
Week 9 3/3 Vulnerability and Robustness of Online Learning
3/5 Online Reinforcement Learning
Week 103/10 Project presentations
3/12 Project presentations HW4 due.

Gradings

  • Homework – (4*15%) 60%

  • Paper presentation - 10%

  • Final project – (proposal 5%, presentation 10%, report 15%) 30%

  • Total – 100%

Resources

Suggested readings:
A Modern Introduction to Online Learning, Francesco Orabona.
Bandit Algorithms by Tor Lattimore and Csaba Szepesvári