Algorithmic Statistics, MIT, Fall 2025

Basics

Lectures

Lecture number Date Lecture topic Notes Video
1 9/3/25 intro, le cam, uniformity testing lower bound draft
2 9/8/25 overview, linear and logistic regression, start sparse regression draft
3 9/10/25 sparse regression, compressed sensing Moitra book, Ch. 5
4 9/15/25 learning a gaussian and a product distribution – tv versus parameter learning
5 9/17/25 introduction to MRFs, ising uniformity testing
6 9/22/25 tree-structured graphical models I – belief propagation
7 9/24/25 tree-structured graphical models II – chow-liu, fano
8 9/29/25 parameter learning MRFs
9 10/1/25 tv learning MRFs, tournament
10 10/6/25 kesten-stigum bound, temperature
11 10/8/25 log sobolev – sampling and concentration of measure
12 10/15/25 svd, pca, best rank-one approximation (steurer notes)
13 10/20/25 spectral clustering I: gaussian mixtures
14 10/22/25 spectral clustering II: stochastic block model
15 10/27/25 stochastic block model robustness and ultra-sparse regime – grothendieck inequality and sdp
16 10/29/25 matrix completion
17 11/3/25 tensor decomposition I: Jenrich’s algorithm
18 11/5/25 tensor decomposition II: ICA, HMMs, and friends
19 11/12/25 robust mean estimation via filter
20 11/17/25 robust learning ising models
21 11/19/25 SQ I
22 11/24/25 SQ II – friends of SQ including low degree, overlap gap, SoS
23 11/26/25 planted clique – robust sparse mean estimation
24 12/1/25 lwe reduction??
25 12/3/25 (sam traveling – possibly cancel class or rehearse presentations)
26 12/8/25 project presentations
27 12/10/25 project presentations

Assignments