Momentum with Variance Reduction for Nonconvex Composition Optimization

by   Ziyi Chen, et al.

Composition optimization is widely-applied in nonconvex machine learning. Various advanced stochastic algorithms that adopt momentum and variance reduction techniques have been developed for composition optimization. However, these algorithms do not fully exploit both techniques to accelerate the convergence and are lack of convergence guarantee in nonconvex optimization. This paper complements the existing literature by developing various momentum schemes with SPIDER-based variance reduction for non-convex composition optimization. In particular, our momentum design requires less number of proximal mapping evaluations per-iteration than that required by the existing Katyusha momentum. Furthermore, our algorithm achieves near-optimal sample complexity results in both non-convex finite-sum and online composition optimization and achieves a linear convergence rate under the gradient dominant condition. Numerical experiments demonstrate that our algorithm converges significantly faster than existing algorithms in nonconvex composition optimization.


page 1

page 2

page 3

page 4


Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization

Two new stochastic variance-reduced algorithms named SARAH and SPIDER ha...

Shuffling Gradient-Based Methods with Momentum

We combine two advanced ideas widely used in optimization for machine le...

Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization

The problem of minimizing sum-of-nonconvex functions (i.e., convex funct...

Momentum-based variance-reduced proximal stochastic gradient method for composite nonconvex stochastic optimization

Stochastic gradient methods (SGMs) have been extensively used for solvin...

Momentum Q-learning with Finite-Sample Convergence Guarantee

Existing studies indicate that momentum ideas in conventional optimizati...

Provably Faster Algorithms for Bilevel Optimization

Bilevel optimization has been widely applied in many important machine l...

Riemannian stochastic recursive momentum method for non-convex optimization

We propose a stochastic recursive momentum method for Riemannian non-con...