Fall 2013

Analytic Methods for Supervised Learning II

Tuesday, September 10th, 2013 9:00 am10:30 am

Add to Calendar

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.