Timezone: »

Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure
Alberto Bietti · Julien Mairal

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #174

Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal with stochastic perturbations of input data, induced for example by data augmentation. In such cases, the objective is no longer a finite sum, and the main candidate for optimization is the stochastic gradient descent method (SGD). In this paper, we introduce a variance reduction approach for these settings when the objective is composite and strongly convex. The convergence rate outperforms SGD with a typically much smaller constant factor, which depends on the variance of gradient estimates only due to perturbations on a single example.

Author Information

Alberto Bietti (Inria)
Julien Mairal (Inria)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors