Evolutionary Cutting Planes

Jérémie Decock 1, 2 David L. Saint-Pierre 2, 1 Olivier Teytaud 1, 2
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : The Cutting Plane method is a simple and efficient method for optimizing convex functions in which subgradients are available. This paper proposes several methods for parallelizing it, in particular using a typically evolutionary method, and compares them experimentally in a well-conditioned and ill-conditioned settings.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01194540
Contributor : Olivier Teytaud <>
Submitted on : Monday, September 7, 2015 - 11:07:27 AM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Tuesday, December 8, 2015 - 10:51:45 AM

File

EAsource.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01194540, version 1

Citation

Jérémie Decock, David L. Saint-Pierre, Olivier Teytaud. Evolutionary Cutting Planes. Artificial Evolution (EA2015), 2015, Lyon, France. ⟨hal-01194540⟩

Share

Metrics

Record views

466

Files downloads

205