(Fall 2025) Course Overview & Syllabus

6.7480 Information Theory: From Coding to Learning

Introduces fundamentals of information theory and its applications to contemporary problems in statistics, machine learning, and computer science. A thorough study of information measures, including Fisher information, f-divergences, their convex duality, and variational characterizations. Covers information-theoretic treatment of inference, hypothesis testing and large deviations, universal compression, channel coding, lossy compression, and strong data-processing inequalities.

Methods are applied to deriving PAC-Bayes bounds, GANs, tokenization and quantization of LLMs, and regret inequalities in machine learning, metric and non-parametric estimation in statistics, communication complexity, and computation with noisy gates in computer science. Fast-paced journey through a recent textbook with the same title. For a communication-focused version, consider 6.7470.

Schedule Information

Lectures

Time: Monday and Wednesday 11:00 AM - 12:30 PM
Location: Room 4-237
First Lecture: Wednesday, September 3

Contact Information

Office Hours

Yury (Instructor)

By appointment, email yp@mit.edu

Anzo

Tuesdays, 9-10a (room: see weekly announcement)

Nikita

Tuesdays, 4-5pm (room: see weekly announcement)

Reading Materials

Main Reading

Primary Textbook: Information Theory: From Coding to Learning
by Y. Polyanskiy, Y. Wu
(will be shared on Canvas)

Supplementary (Optional) Resources

Information Theory: Elements of Information Theory
by T. Cover and J. Thomas
Statistics: Introduction to Non-parametric Estimation
by A. B. Tsybakov

Assessment & Grading

Component Weight Details
Weekly Problem Sets 50% Due Wednesdays at 10pm (unless stated otherwise)
Midterm Exam 45% In-class exam
Participation Bonus 5% Class interaction, office hours, independent reading
Final Exam None Last PSet is larger and worth double points

Course Policies

Problem Set Policies

Attendance Policy

Graduate Class Expectations

This is a graduate class, so interaction in class and office hours, independent reading, and discussing research projects all contribute to grade (participation bonus).