Spring 2026

Published

26 January 2026

Meeting Schedule

Note: We will meet ***weekly on Mondays, 3:00-05:00PM***.
Date	Room	Topic	Reading	Presenter
2^nd February	2-426	kickoff meeting		NSH
9^th February	2-426	mathematics for ML, supervised learning	Bach (2024): Ch. 1, 2	SB
~~16^th February~~	~~2-426~~	*canceled*—presidents’ day
23^rd February	2-426	linear least-squares, empirical risk minimization	Bach (2024): Ch. 3, 4
2^nd March	2-426	research connections
9^th March	2-426	optimization for ML	Bach (2024): Ch. 5
~~16^th March~~	~~2-426~~	*canceled*—spring break
23^rd March	2-426	research connections
30^th March	2-426	local averaging methods, kernel methods
6^th April	2-426	research connections
13^th April	2-426	sparse methods, neural networks	Bach (2024): Ch. 8, 9
20^th April	2-426	research connections
27^th April	2-426	ensemble learning, online learning and bandits	Bach (2024): Ch. 10, 11
4^th May	2-426	research connections

This term, we will continue to discuss topics in statistical learning theory and statistical machine learning, primarily drawing material from the text by Bach (2024), possibly to be supplemented by topics covered in others (e.g., Bickel and Doksum 2015; Duchi 2024). Note that we will switch weekly between presentations of materials from the relevant texts and informal research presentations that cover the relationship between topics most recently discussed and ongoing projects in this group.

Bach (2024): Ch. 1 (mathematical preliminaries), 2 (supervised learning), 3 (linear least-squares), 4 (empirical risk minimization), 5 (optimization for machine learning), 6 (local averaging methods), 7 (kernel methods), 8 (sparse methods), 9 (neural networks), 10 (ensemble learning), 11 (from online learning to bandits), 12 (over-parametrized models)
Bickel and Doksum (2015): Ch. 7 (tools for asymptotic analysis), 9 (inference in semi-parametric models), 12 (prediction and machine learning)
Duchi (2024): Ch. 2 (basics of information theory), 4 (concentration inequalities), 5 (generalization and stability), 8 (minimax lower bounds),

References

Bach, Francis. 2024. Learning Theory from First Principles. https://www.di.ens.fr/%7Efbach/ltfp_book.pdf.

Bickel, Peter J, and Kjell A Doksum. 2015. Mathematical Statistics: Basic Ideas and Selected Topics, Volume II. CRC Press. https://doi.org/10.1201/b19822.

Duchi, John. 2024. Statistics and Information Theory. https://web.stanford.edu/class/stats311/lecture-notes.pdf.