Sorry, you need to enable JavaScript to visit this website.

Sketching for Large-Scale Learning of Mixture Models

Citation Author(s):
Anthony Bourrier, Remi Gribonval, Patrick Perez
Submitted by:
Nicolas Keriven
Last updated:
21 March 2016 - 4:00am
Document Type:
Presentation Slides
Document Year:
2016
Event:
Presenters:
Nicolas Keriven
Paper Code:
1365

Abstract

Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a "compressive learning" framework where we first sketch the data by computing random generalized moments of the underlying probability distribution, then estimate mixture model parameters from the sketch using an iterative algorithm analogous to greedy sparse signal recovery. We exemplify our framework with the sketched estimation of Gaussian Mixture Models (GMMs). We experimentally show that our approach yields results comparable to the classical Expectation-Maximization (EM) technique while requiring significantly less memory and fewer computations when the number of database elements is large. We report large-scale experiments in speaker verification, where our approach makes it possible to fully exploit a corpus of 1000 hours of speech signal to learn a universal background model at scales computationally inaccessible to EM.

pres.pdf

PDF icon pres.pdf (502)
Media Folder: 
up
0 users have voted: