Statistics 311/Electrical Engineering 377: Information Theory and Statistics
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 26 | Overview, basic divergence measures | LN 1-2, CT 2* |
| 2 | Thu, Sep 28 | Chain rules and general divergence measures | LN 2, CT 2 |
| 3 | Tue, Oct 3 | Le Cam and Fano inequalities, concentration | LN 2, 4.1, RM 2.3 |
| 4 | Thu, Oct 5 | Sub-exponential concentration | LN 4.1, 4.2, RM 2.4 |
| 5 | Tue, Oct 10 | Martingale methods and uniformity | LN 4.2, 4.3, RM 2 |
| 6 | Thu, Oct 12 | Uniform laws, beginning PAC-Bayes bounds | LN 5.1, 5.2 |
| 7 | Tue, Oct 17 | PAC-Bayes bounds and bits of interactive data analysis | LN 5.2 |
| 8 | Thu, Oct 19 | Interactive data analysis | LN 5.3 |
| 9 | Tue, Oct 24 | Privacy and disclusure limitation | LN 7.1, 7.2 |
| 10 | Thu, Oct 26 | Privacy: composition guarantees | LN 7.2, 7.3 |
| 11 | Tue, Oct 31 | Privacy: inverse sensitivity | LN 7.4 |
| 12 | Thu, Nov 2 | Le Cam/Fano methods | LN 8.1–8.4 |
| NA | Tue, Nov 7 | No class (democracy day) | |
| 13 | Thu, Nov 9 | Assouad's method | LN 8.5–8.6 |
| 14 | Tue, Nov 14 | Strong data processing inequalities | LN 9.1–9.2 |
| 15 | Thu, Nov 16 | Constrained lower bounds | LN 9.1–9.2 |
| 16 | Tue, Nov 28 | Loss functions and entropy | LN 11.1–11.3 |
| 17 | Thu, Nov 30 | Calibration and proper losses | LN 12.1–12.3 |
| 18 | Tue, Dec 5 | Surrogate risk consistency | |
| 19 | Thu, Dec 7 | Presentations |
|
Abbreviation key
|