CS 8803: Sequence Prediction (Spring 2026)
Welcome to the course website for CS 8803 Sequence Prediction at Georgia Tech.
Course Information
- Instructor: Jacob Abernethy
- Time: Fridays 11:00 AM - 1:45 PM
- Location: Skiles 168
- Office Hours: Mondays 3:30 PM (2nd floor of CODA). Note: Please give at least one hour prior warning if you plan to attend.
Description
This course explores the theoretical foundations of sequential prediction and decision making. We cover a range of topics from classical information theory and algorithmic complexity (Kolmogorov complexity, Solomonoff Induction) to modern generative models (Transformers, Discrete Diffusion Models). The course emphasizes mathematical rigor and the connections between different frameworks.
The course is designed for mathematically-trained graduate students who are interested in engaging in modern research in these areas.
Topics
This is just a general list of topics. Adjustments will be made according to student interest and availability of guest lecturers.
- Computability, Kolmogorov Complexity, Solomonoff Induction
- Online learning, regret minimization, repeated games
- Information Theory, compression, martingales, other stochastic processes
- Sequential betting strategies, portfolio optimization
- Multi-armed bandits, refinforcement learning, exploration strategies, policy optimization
- Sequence models, Hidden Markov Models, Kalman filtering, optimal control
- Modern Sequence Models: RNNs, transformers, discrete diffusion models
Links
© 2026 Jacob Abernethy