Multi-Level Composite Stochastic Optimization via Nested Variance Reduction

by   Junyu Zhang, et al.

We consider multi-level composite optimization problems where each mapping in the composition is the expectation over a family of random smooth mappings or the sum of some finite number of smooth mappings. We present a normalized proximal approximate gradient (NPAG) method where the approximate gradients are obtained via nested stochastic variance reduction. In order to find an approximate stationary point where the expected norm of its gradient mapping is less than ϵ, the total sample complexity of our method is O(ϵ^-3) in the expectation case, and O(N+√(N)ϵ^-2) in the finite-sum case where N is the total number of functions across all composition levels. In addition, the dependence of our total sample complexity on the number of composition levels is polynomial, rather than exponential as in previous work.


page 1

page 2

page 3

page 4


Nonconvex Stochastic Nested Optimization via Stochastic ADMM

We consider the stochastic nested composition optimization problem where...

A Stochastic Composite Gradient Method with Incremental Variance Reduction

We consider the problem of minimizing the composition of a smooth (nonco...

Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Rates

In this paper, we study smooth stochastic multi-level composition optimi...

A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization

We propose a projection-free conditional gradient-type algorithm for smo...

Finding Local Minima via Stochastic Nested Variance Reduction

We propose two algorithms that can find local minima faster than the sta...

Optimal Algorithms for Stochastic Multi-Level Compositional Optimization

In this paper, we investigate the problem of stochastic multi-level comp...

Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization

We develop two new stochastic Gauss-Newton algorithms for solving a clas...