| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Linear Convergence of Evolution Strategies with Derandomized Sampling Beyond Quasi-Convex Functions
Abstract : We study the linear convergence of a simple evolutionary algorithm on non quasi-convex functions on continuous domains. Assumptions include an assumption on the sampling performed by the evolutionary algorithm (supposed to cover efficiently the neighborhood of the current search point), the conditioning of the objective function (so that the probability of improvement is not too low at each time step, given a correct step size), and the unicity of the optimum.
Cited literature [13 references]
https://hal.inria.fr/hal-00907671
Contributor : Jérémie Decock <>
Submitted on : Thursday, November 21, 2013 - 3:45:47 PM
Last modification on : Tuesday, April 21, 2020 - 1:05:05 AM
Document(s) archivé(s) le : Saturday, February 22, 2014 - 4:41:18 AM
Contributor : Jérémie Decock <>
Submitted on : Thursday, November 21, 2013 - 3:45:47 PM
Last modification on : Tuesday, April 21, 2020 - 1:05:05 AM
Document(s) archivé(s) le : Saturday, February 22, 2014 - 4:41:18 AM
File
linearConvergence.pdf
Files produced by the author(s)