1 Overview and Two Open Problems  
2-4 Principal Component Analysis in High Dimensions and the Spike Model  
5-7 Graphs, Diffusion Maps, and Semi-supervised Learning  
8-11 Spectral Clustering and Cheeger’s Inequality Problem Set 1 due
12-14 Concentration Inequalities, Scalar and Matrix Versions Problem Set 2 due
15-16 Johnson-Lindenstrauss Lemma and Gordon’s Theorem Problem Set 3 due
17 Local Convergence of Graphs and Enumeration of Spanning Trees  
18-19 Compressed Sensing and Sparse Recovery Project Abstract due
20 Group Testing and Error-Correcting Codes Problem Set 4 due
21 Approximation Algorithms and Max-Cut  
22 Community Detection and the Stochastic Block Model Problem Set 5 due
23 Synchronization Problems and Alignment  
24 Project Presentations Project Presentations
25 Project Report Project Report due

Course Info

Learning Resource Types

assignment Problem Sets
notes Lecture Notes
co_present Instructor Insights