Many contemporary problems in data science require an understanding of high-dimensional statistics and probability to tackle the issues at hand. The goal of this course will be to give a tour through several mathematical phenomena that arise in high-dimensions and describe techniques to analyze them. Topics include concentration of measure, dimension reduction, restricted isometry, principal component analysis, and VC dimension, and applications to areas such as statistical inference (including linear regression and compressed sensing), empirical processes, and property testing.

Lectures are on every Tuesday and Thursday, 2 pm to 3:30 pm, at CSA 252. The first class is on Thursday, August 10.

**High-Dimensional Probability**. Roman Vershynin (book manuscript).-
**Ten Lectures and Forty-Two Open Problems in the Mathematics of Data Science**. Afonso S. Bandeira (lecture notes). -
**High Dimensional Statistics.**Philippe Rigollet (lecture notes). -
**Probability in High Dimensions.**Ramon van Handel (lecture notes).