Linear Convergence of Comparison-based Step-size Adaptive Randomized Search via Stability of Markov Chains

Anne Auger 1 Nikolaus Hansen 1
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : In this paper, we consider comparison-based stochastic algorithms for solving numerical optimisation problems. We consider a specific subclass of algorithms called comparison-based step-size adaptive randomized search (CB-SARS), where the state variables at a given iteration are a vector of the search space and a positive parameter, the step-size, typically controlling the overall variance of the underlying search distribution. We investigate the linear convergence of CB-SARS on scaling-invariant objective functions. Scaling-invariant functions preserve the ordering of points with respect to their function value when the points are scaled with the same positive parameter (the scaling is done w.r.t. a fixed reference point). This class of functions includes norms composed with strictly increasing functions as well as non quasi-convex and non-continuous functions. On scaling-invariant functions, we show the existence of a homogeneous Markov Chain, as a consequence of natural invariance properties of CB-SARS (essentially scale-invariance and invariance to strictly increasing transformation of the objective function). We then derive sufficient conditions for asymptotic global linear convergence of CB-SARS, expressed in terms of different stability conditions of the normalised homogeneous Markov chain (irreducibility, positivity, Harris recurrence, geometric ergodicity) and thus define a general methodology for proving global linear convergence of CB-SARS algorithms on scaling-invariant functions.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-00877160
Contributor : Anne Auger <>
Submitted on : Friday, April 25, 2014 - 4:15:16 PM
Last modification on : Sunday, July 21, 2019 - 1:48:11 AM
Long-term archiving on : Monday, April 10, 2017 - 4:55:44 PM

Files

LinearCVASARSMethodology.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00877160, version 4
  • ARXIV : 1310.7697

Citation

Anne Auger, Nikolaus Hansen. Linear Convergence of Comparison-based Step-size Adaptive Randomized Search via Stability of Markov Chains. 2014. ⟨hal-00877160v4⟩

Share

Metrics

Record views

518

Files downloads

67