paper-with-me

Papers

A Stochastic Composite Gradient Method with Incremental Variance Reduction

2019-06-24 · NeurIPS 2019 12 · Junyu Zhang, Lin Xiao

We consider the problem of minimizing the composition of a smooth (nonconvex) function and a smooth vector mapping, where the inner mapping is in the form of an expectation over some random variable or a finite sum. We propose a stochastic composite gradient method that employs an incremental variance-reduced estimator for both the inner vector mapping and its Jacobian. We show that this method achieves the same orders of complexity as the best known first-order methods for minimizing expected-value and finite-sum nonconvex functions, despite the additional outer composition which renders the composite gradient estimator biased. This finding enables a much broader range of applications in machine learning to benefit from the low complexity of incremental variance-reduction methods.

📄 PDF Abstract BibTeX arXiv:1906.10186

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Stochastic Variable Metric Proximal Gradient with variance reduction for non-convex composite optimization

2023-01-02 · Gersende Fort, Eric Moulines

This paper introduces a novel algorithm, the Perturbed Proximal Preconditioned SPIDER algorithm (3P-SPIDER), designed to solve finite sum non-convex composite optimization. It is a stochastic Variable Metric Forward-Back…

Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise

2019-01-25 · Andrei Kulunchakov, Julien Mairal

In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. More precisely, we interpret a larg…

Stochastic Optimization

Variance-Reduced Proximal Stochastic Gradient Descent for Non-convex Composite optimization

2016-06-02 · Xiyu Yu, DaCheng Tao

Here we study non-convex composite optimization: first, a finite-sum of smooth but non-convex functions, and second, a general function that admits a simple proximal mapping. Most research on stochastic methods for compo…

Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure

2016-10-04 · NeurIPS 2017 · Alberto Bietti, Julien Mairal

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 d…

Data AugmentationStochastic Optimization

Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure

2017-12-01 · NeurIPS 2017 12 · Alberto Bietti, Julien Mairal

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 d…

Data AugmentationStochastic Optimization