Duality-free Methods for Stochastic Composition Optimization

10/26/2017
by   Liu Liu, et al.
0

We consider the composition optimization with two expected-value functions in the form of 1/n∑_i = 1^n F_i(1/m∑_j = 1^m G_j(x))+R(x), which formulates many important problems in statistical learning and machine learning such as solving Bellman equations in reinforcement learning and nonlinear embedding. Full Gradient or classical stochastic gradient descent based optimization algorithms are unsuitable or computationally expensive to solve this problem due to the inner expectation 1/m∑_j = 1^m G_j(x). We propose a duality-free based stochastic composition method that combines variance reduction methods to address the stochastic composition problem. We apply SVRG and SAGA based methods to estimate the inner function, and duality-free method to estimate the outer function. We prove the linear convergence rate not only for the convex composition problem, but also for the case that the individual outer functions are non-convex while the objective function is strongly-convex. We also provide the results of experiments that show the effectiveness of our proposed methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/06/2018

Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem

In this paper, we consider the convex and non-convex composition problem...
research
07/19/2022

Riemannian Stochastic Gradient Method for Nested Composition Optimization

This work considers optimization of composition of functions in a nested...
research
11/14/2014

Stochastic Compositional Gradient Descent: Algorithms for Minimizing Compositions of Expected-Value Functions

Classical stochastic gradient methods are well suited for minimizing exp...
research
11/13/2017

Variance Reduced methods for Non-convex Composition Optimization

This paper explores the non-convex composition optimization in the form ...
research
06/20/2021

Robust Regression via Model Based Methods

The mean squared error loss is widely used in many applications, includi...
research
07/13/2018

Global optimization test problems based on random field composition

The development and identification of effective optimization algorithms ...
research
07/22/2019

Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization

We consider a generic empirical composition optimization problem, where ...

Please sign up or login with your details

Forgot password? Click here to reset