Applications of combinatorial representation theory to machine learning

05/05/2015 - 12:15pm
05/05/2015 - 1:10pm
Lily Silverstein (CGU)

Some machine learning problems are naturally modeled by probability distributions (or other data) defined over a finite group. In this case the generalized Fourier transform, based on irreducible group representations, is a useful tool for designing efficient algorithms. In the case of the symmetric group, we can use combinatorial objects like Young diagrams to define an analogue to bandlimiting. Finally, I will talk about how certain probabilistic inferences can be performed directly in the Fourier domain, by considering the combinatorial decomposition of tensor products of representations. This talk is expository and based mainly on work done by Jonathan Huang and Risi Kondor.

Mudd Science Library 126, Pomona College

Claremont Graduate University | Claremont McKenna | Harvey Mudd | Pitzer | Pomona | Scripps
Proudly Serving Math Community at the Claremont Colleges Since 2007
Copyright © 2018 Claremont Center for the Mathematical Sciences