Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes

Abstract

We propose a structure-adaptive variant of the state-of-the-art stochastic variance-reduced gradient algorithm Katyusha for regularized empirical risk minimization. The proposed method is able to exploit the intrinsic low-dimensional structure of the solution, such as sparsity or low rank which is enforced by a non-smooth regularization, to achieve even faster convergence rate. This provable algorithmic improvement is done by restarting the Katyusha algorithm according to restricted strong-convexity constants. We demonstrate the effectiveness of our approach via numerical experiments.

Cited by in corpus (4)

• Faster First-Order Primal-Dual Methods for Linear Programming using Restarts and Sharpness
• The Practicality of Stochastic Optimization in Imaging Inverse Problems
• A unified variance-reduced accelerated gradient method for convex optimization
• A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems