Noisy Optimization: Fast Convergence Rates with Comparison-Based Algorithms

Derivative Free Optimization is known to be an efficient and robust method to tackle the black-box optimization problem. When it comes to noisy functions, classical comparison-based algorithms are slower than gradient-based algorithms. For quadratic functions, Evolutionary Algorithms without large m...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2016-04
Hauptverfasser:	Marie-Liesse Cauwet, Teytaud, Olivier
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Evolutionary algorithms Mutation Optimization Quadratic equations
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!