Fall 2025

Published

26 January 2026

Meeting Schedule

Note: We will meet biweekly **on Mondays**, 10:00AM-12:00PM, *usually* in HSPH 2-426.
Date	Room	Topic	Reading	Presenter
8^th September	2-426	tail and concentration bounds, uniform laws of large numbers	Wainwright (2019): Ch. 2, 4	SB
22^nd September	2-426	metric entropy, minimax lower bounds	Wainwright (2019): Ch. 5, 15	HL
6^th October	2-426	regularized regression and M-estimation	Wainwright (2019): Ch. 7, 9	CT
20^th October	2-426	RKHS, non-parametric least squares	Wainwright (2019): Ch. 12, 13	CJ
3^rd November	2-426	non-parametric least squares, supervised learning	Wainwright (2019): 13, Hardt and Recht (2022) Ch. 3	CJ, NSH
17^th November	2-426	representations and features, optimization	Hardt and Recht (2022) Ch. 4, 5	SB
8^th December	FXB-G03	generalization, deep learning	Hardt and Recht (2022) Ch. 6, 7	CT

This term, we will discuss topics in high-dimensional statistics and statistical machine learning, with material drawn from the texts Wainwright (2019) and Hardt and Recht (2022) (see details below). We will continue along this theme in the following term.

Wainwright (2019): Ch. 2 (tail and concentration bounds), 4 (uniform laws of large numbers), 5 (metric entropy), 7 (sparse linear models), 9 (regularized M-estimators), 12 (RKHS, including kernel ridge regression), 13 (non-parametric least squares), 15 (minimax lower bounds)
Hardt and Recht (2022): Ch. 3 (supervised learning), 4 (representation and features), 5 (optimization), 6 (generalization), 7 (deep learning)

References

Hardt, Moritz, and Benjamin Recht. 2022. Patterns, Predictions, and Actions: Foundations of Machine Learning. Princeton University Press. https://mlstory.org/.

Wainwright, Martin J. 2019. High-Dimensional Statistics: A Non-Asymptotic Viewpoint. Cambridge University Press. https://doi.org/10.1017/9781108627771.