# A Generic Acceleration Framework for Stochastic Composite Optimization

@inproceedings{Kulunchakov2019AGA, title={A Generic Acceleration Framework for Stochastic Composite Optimization}, author={Andrei Kulunchakov and Julien Mairal}, booktitle={NeurIPS}, year={2019} }

In this paper, we introduce various mechanisms to obtain accelerated first-order stochastic optimization algorithms when the objective function is convex or strongly convex. Specifically, we extend the Catalyst approach originally designed for deterministic objectives to the stochastic setting. Given an optimization method with mild convergence guarantees for strongly convex problems, the challenge is to accelerate convergence to a noise-dominated region, and then achieve convergence with an… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

#### Citations

##### Publications citing this paper.

SHOWING 1-8 OF 8 CITATIONS

## Adaptive Catalyst for smooth convex optimization

VIEW 6 EXCERPTS

CITES BACKGROUND & METHODS

HIGHLY INFLUENCED

## Exponential Step Sizes for Non-Convex Optimization

VIEW 1 EXCERPT

CITES METHODS

## Inexact Tensor Methods with Dynamic Accuracies

VIEW 1 EXCERPT

CITES BACKGROUND

## On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings

VIEW 1 EXCERPT

CITES METHODS

## Decentralized and Parallelized Primal and Dual Accelerated Methods for Stochastic Convex Programming Problems

VIEW 1 EXCERPT

CITES BACKGROUND

## Optimal Decentralized Distributed Algorithms for Stochastic Convex Optimization

VIEW 2 EXCERPTS

CITES BACKGROUND

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 58 REFERENCES

## Introductory Lectures on Convex Optimization - A Basic Course

VIEW 13 EXCERPTS

HIGHLY INFLUENTIAL

## Katyusha: the first direct acceleration of stochastic gradient methods

VIEW 5 EXCERPTS

HIGHLY INFLUENTIAL

## Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL

## Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL