Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Incremental Without Replacement Sampling in Nonconvex Optimization

Edouard Pauwels 1
1 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage
IRIT - Institut de recherche en informatique de Toulouse
Abstract : Minibatch decomposition methods for empirical risk minimization are commonly analysed in a stochastic approximation setting, also known as sampling with replacement. On the other hands modern implementations of such techniques are incremental: they rely on sampling without replacement, for which available analysis are much scarcer. We provide convergence guaranties for the latter variant by analysing a versatile incremental gradient scheme. For this scheme, we consider constant, decreasing or adaptive step sizes. In the smooth setting we obtain explicit complexity estimates in terms of epoch counter. In the nonsmooth setting we prove that the sequence is attracted by solutions of optimality conditions of the problem.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Edouard Pauwels <>
Submitted on : Tuesday, June 15, 2021 - 9:39:29 AM
Last modification on : Saturday, June 19, 2021 - 4:06:44 AM


Files produced by the author(s)


  • HAL Id : hal-02896102, version 3
  • ARXIV : 2007.07557


Edouard Pauwels. Incremental Without Replacement Sampling in Nonconvex Optimization. 2021. ⟨hal-02896102v3⟩



Record views


Files downloads