Wed. 12-12:50, Rm Mth 0201
Eric Slud
Interested participants should get in touch with
us at slud@umd.edu, or vlyzinsk@umd.edu
The main reference we will cover is
High-Dimensional Statistics: A Non-asymptotic Viewpoint, by Martin Wainwright,
Cambridge Univ. Press 2019.
Chapters freely downloadable for students through the UMD Libraries website.
Older related statistical papers can be found in the old RIT website RIT on Statistics of Models with Increasing Parameter Dimension, F05
Other recommended books:
Boucheron, S., Lugosi, G., & Massart, P. (2013). Concentration inequalities: a non asymptotic theory of independence
-- https://www.amazon.com/Concentration-Inequalities-Nonasymptotic-Theory-Independence/dp/019876765X
Horn, Roger A., and Charles R. Johnson. Matrix analysis. Cambridge university press, 2012.
--
https://www.amazon.com/Matrix-Analysis-Second-Roger-Horn/dp/0521548233
Schedule of Talks
Note: where available, links to slides are in the names and dates of past speakers
Ch.1 of Wainwright: Shitao Fan, Sept. 4
Ch.2 of Wainwright: Tail inequality material involving sub-Gaussian, sub-exponential (Sec.2.1),
Nick Wu, Sept. 11
Ch.3 on Concentration of Measure, Vince Lyzinski, Sept. 18
Ch.2 of Wainwright, martingale material (Sec.2.2 + background) Eric Slud, Sept.25
Ch.7 on Sparse Linear Models (with some Lasso background), Chugang Yi, Oct. 2 & 9
Ch.4 of Wainwright, Uniform Laws of Large Numbers and Rademacher Complexity, Perrin Ruth, Oct. 16
Ch.5 on Metric Entropy and Gaussian processes, Willie Dong, Oct. 23
Ch.8 on Principal Component Analysis, John McMenimon, October 30 and November 6
Ch.6 on Random Matrices and Covariance Estimation: James Kwon, began on Nov.6, resumed Nov.13
Ch.10 on Matrix Estimation with Rank Constraints, Zhirui Li, November 20
Ch.11 on Graphical Models, Kartik Ravisankar, December 4