Black-box optimization of noisy functions with unknown smoothness

We study the problem of black-box optimization of a function f of any dimension, given function evaluations perturbed by noise. The function is assumed to be locally smooth around one of its global optima, but this smoothness is unknown. Our contribution is an adaptive optimization algorithm, POO or parallel optimistic optimization, that is able to deal with this setting. POO performs almost as well as the best known algorithms requiring the knowledge of the smoothness. Furthermore, POO works for a larger class of functions than what was previously considered, especially for functions that are difficult to optimize, in a very precise sense. We provide a finite-time analysis of POO's performance, which shows that its error after n evaluations is at most a factor of √ln n away from the error of the best known optimization algorithms using the knowledge of the smoothness.

[1]  Csaba Szepesvári,et al.  –armed Bandits , 2022 .

[2]  Adam D. Bull,et al.  Adaptive-treed bandits , 2013, 1302.2489.

[3]  Eli Upfal,et al.  Multi-Armed Bandits in Metric Spaces ∗ , 2008 .

[4]  Rémi Munos,et al.  Optimistic Optimization of Deterministic Functions , 2011, NIPS 2011.

[5]  Philippe Preux,et al.  Bandits attack function optimization , 2014, 2014 IEEE Congress on Evolutionary Computation (CEC).

[6]  Alexandre Proutière,et al.  Unimodal Bandits without Smoothness , 2014, ArXiv.

[7]  Rémi Munos,et al.  Pure exploration in finitely-armed and continuous-armed bandits , 2011, Theor. Comput. Sci..

[8]  Rémi Munos,et al.  From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning , 2014, Found. Trends Mach. Learn..

[9]  Rémi Munos,et al.  Stochastic Simultaneous Optimistic Optimization , 2013, ICML.

[10]  Alessandro Lazaric,et al.  Online Stochastic Optimization under Correlated Bandit Feedback , 2014, ICML.

[11]  Jia Yuan Yu,et al.  Lipschitz Bandits without the Lipschitz Constant , 2011, ALT.

[12]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[13]  Rémi Munos,et al.  Bandit Algorithms for Tree Search , 2007, UAI.

[14]  Aleksandrs Slivkins,et al.  Multi-armed bandits on implicit metric spaces , 2011, NIPS.

[15]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[16]  Alexandre Proutière,et al.  Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms , 2014, ICML.