In probability theory, an empirical process is a stochastic process that describes the proportion of objects in a system in a given state. In this seminar we are interested in the sup of emprical process and it's applications in statistical machine learning. (Besides reading textbook, we'll also go through recent papers using these theorems.)
Topics:
Detailed Syllabus:here (Including references and readings)
Zoom Link:here
Contact: yplu [*at*] stanford [*at*] edu
找不到黄图
Van Der Vaart A W, Wellner J A. Weak convergence and empirical processes. Springer, New York, NY, 1996: 16-28.
Geer S A, van de Geer S. Empirical Processes in M-estimation. Cambridge university press, 2000.
Stats300b Theory of Statisticss II by John Duchi
Seminar on High dimensional probability on bilibili
Note: slide1
Note: Chapter 1.1-1.3 in pdf
Note: Chapter 1 of pdf
Reference: Chapter 2 of Weak convergence and emprical process book.
Exercise:
Note: pdf
Slide: Neural Scaling Law (TO DO).
Note: Learning rate of ERM problem.
Further Reading:
Examples
Notes: TO DO
Examples
Notes: TO DO
Notes: TO DO
Notes: TO DO
Examples
Notes: TO DO