Mathematics 697AM - ST-Foundatns/AnalysisMachLrng

In this course we will cover some of fundamental ideas from analysis, statistics, and optimization that are relevant to methods in machine learning and statistical inference. The class will cover not only the most well known linear methods, but also the more recently developed nonlinear methods that use the intuition from classical topics in PDE and the calculus of variations, such as the theory minimal surfaces, optimal transport, and gradient flows.

Requirements: Undergraduate real analysis (basics of metric spaces, integration), basic probability (distributions, random variables), strong background in calculus and linear algebra. Familiarity with one or more of the following is a plus: measure theory, differentiable manifolds, basic programming skills and/or familiarity with mathematica, mathlab, SciPy.

Open to Graduate students only.