Skip to Main content Skip to Navigation
Documents associated with scientific events

Noisy Optimization

Sandra Astete-Morales 1, 2 Marie-Liesse Cauwet 1, 2 Adrien Couetoux 1, 2 Jérémie Decock 1, 2 Jialin Liu 1, 2 Olivier Teytaud 1, 2
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 : The black box complexity of noisy-optimization is a great research area, with many real-world applications. Various criteria can be used: cumulative regret, simple regret, uniform rates. We discuss the impact of the use of second order information (improved rates under low noise assumption), or local sampling (slower simple regret convergence), or evolutionary optimization with revaluations (as efficient as mathematical programming in some cases with cumulative regret).
Document type :
Documents associated with scientific events
Complete list of metadata
Contributor : Olivier Teytaud Connect in order to contact the contributor
Submitted on : Sunday, July 14, 2013 - 3:00:07 PM
Last modification on : Thursday, July 8, 2021 - 3:48:44 AM
Long-term archiving on: : Tuesday, October 15, 2013 - 4:08:57 AM


Files produced by the author(s)


  • HAL Id : hal-00844305, version 1


Sandra Astete-Morales, Marie-Liesse Cauwet, Adrien Couetoux, Jérémie Decock, Jialin Liu, et al.. Noisy Optimization. Dagstuhl seminar 13271, 2013, Dagstuhl, Germany. 2013. ⟨hal-00844305⟩



Les métriques sont temporairement indisponibles