A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip - Inria EPFL Access content directly
Conference Papers Advances in Neural Information Processing Systems Year : 2021

A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip

Abstract

We introduce the "continuized" Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter. The two variables continuously mix following a linear ordinary differential equation and take gradient steps at random times. This continuized variant benefits from the best of the continuous and the discrete frameworks: as a continuous process, one can use differential calculus to analyze convergence and obtain analytical expressions for the parameters; and a discretization of the continuized process can be computed exactly with convergence rates similar to those of Nesterov original acceleration. We show that the discretization has the same structure as Nesterov acceleration, but with random parameters. We provide continuized Nesterov acceleration under deterministic as well as stochastic gradients, with either additive or multiplicative noise. Finally, using our continuized framework and expressing the gossip averaging problem as the stochastic minimization of a certain energy function, we provide the first rigorous acceleration of asynchronous gossip algorithms.
Fichier principal
Vignette du fichier
continuized_is_bach (6).pdf (1.02 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03405165 , version 1 (27-10-2021)

Identifiers

  • HAL Id : hal-03405165 , version 1

Cite

Mathieu Even, Raphaël Berthier, Francis Bach, Nicolas Flammarion, Pierre Gaillard, et al.. A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip. NeurIPS 2021 - 35th Conference on Neural Information Processing Systems, Dec 2021, Sydney (virtual), Australia. pp.1-32. ⟨hal-03405165⟩
169 View
136 Download

Share

Gmail Facebook X LinkedIn More