Online Variance Reduction for Stochastic Optimization

conference on learning theory, 2018.

Cited by: 11|Views43
EI

Abstract:

Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible remedy is to employ non-uniform importance sampling techniques, which take the structure of the dataset...More

Code:

Data:

Your rating :
0

 

Tags
Comments