Lecture 1: Analytic Methods for Supervised Learning I
Lecture 2: Analytic Methods for Supervised Learning II
Lecture 3: Analytic Methods for Supervised Learning III
Lecture 4: Analytic Methods for Supervised Learning IV
This series of talks was part of the Real Analysis Boot Camp. Videos for each talk are available through the links above.
Speaker: Adam Klivans, University of Texas, Austin
In this mini-course we will show how to use tools from analysis and probability (e.g., contraction, surface area and limit theorems) to develop efficient algorithms for supervised learning problems with respect to well-studied probability distributions (e.g., Gaussians). One area of focus will be understanding the minimal assumptions needed for convex relaxations of certain learning problems (thought to be hard in the worst-case) to become tractable.