Statistics 311/Electrical Engineering 377: Information Theory and Statistics

John Duchi, Stanford University, Fall 2025

Approximate Course Schedule

The syllabus below suggests what will (likely) be our approximate course schedule. We will likely change a few things around as the course continues, and we may even omit topics or add others as the class desires. While we skip some chapters, we encourage students to at least skim through them (for example, Chapter 3 on exponential families will provide useful background, especially if students have not seen them before). When reading is optional (but provides good context), we will add an asterisk (*) to it.

Lecture Date Topics Reading
1 Tue, Sep 22 Overview, basic divergence measures LN 1-2, CT 2*
2 Thu, Sep 24 Chain rules and general divergence measures LN 2, CT 2
3 Tue, Sep 30 Concentration LN 4.1, RM 2.3
4 Thu, Oct 2 Sub-exponentials, martingale methods LN 4.1, 4.2, RM 2.4
5 Tue, Oct 7 Uniform laws, M-estimation LN 5.1–5.3, RM 2
6 Thu, Oct 9 PAC-Bayes bounds LN 6.1–6.2
7 Tue, Oct 14 Interactive data analysis LN 6.3
8 Thu, Oct 16 Interactive data analysis LN 6.3
9 Tue, Oct 21 Privacy and disclusure limitation LN 8.1, 8.2
10 Thu, Oct 23 Privacy: composition guarantees LN 8.1–8.3
11 Tue, Oct 28 Le Cam/Fano methods LN 9.1–9.4
12 Thu, Oct 30 Assouad's method LN 9
Tue, Nov 4 No class (democracy day)
13 Thu, Nov 6 Strong data processing inequalities LN 10.1
14 Tue, Nov 11 Constrained lower bounds LN 10.1–10.2
15 Thu, Nov 13 Loss functions and entropy LN 14
16 Tue, Nov 18 Calibration and proper losses LN 15.1–15.2
17 Thu, Nov 20 Online learning LN 17
18 Tue, Dec 2 TBD
19 Thu, Dec 4 TBD

Abbreviation key