Global optimization of Lipschitz functions

The goal of the paper is to design sequential strategies which lead to efficient optimization of an unknown function under the only assumption that it has a finite Lipschitz constant. We first identify sufficient conditions for the consistency of generic sequential algorithms and formulate the expected minimax rate for their performance. We introduce and analyze a first algorithm called LIPO which assumes the Lipschitz constant to be known. Consistency, minimax rates for LIPO are proved, as well as fast rates under an additional Holder like condition. An adaptive version of LIPO is also introduced for the more realistic setup where the Lipschitz constant is unknown and has to be estimated along with the optimization. Similar theoretical guarantees are shown to hold for the adaptive LIPO algorithm and a numerical assessment is provided at the end of the paper to illustrate the potential of this strategy with respect to state-of-the-art methods over typical benchmark problems for global optimization.

[1]  B. Shubert.  A Sequential Method Seeking the Global Maximum of a Function , 1972 .

[2]  S. A. Piyavskii.  An algorithm for finding the absolute extremum of a function , 1972 .

[3]  Regina Hunter Mladineo.  An algorithm for finding the global maximum of a multimodal, multivariate function , 1986, Math. Program..

[4]  M. Stein.  Large sample properties of simulations using latin hypercube sampling , 1987 .

[5]  G. T. Timmer,et al.  Stochastic global optimization methods part I: Clustering methods , 1987, Math. Program..

[6]  A. A. Zhigli︠a︡vskiĭ,et al.  Theory of Global Random Search , 1991 .

[7]  Robert L. Smith,et al.  Pure adaptive search in global optimization , 1992, Math. Program..

[8]  C. D. Perttunen,et al.  Lipschitzian optimization without the Lipschitz constant , 1993 .

[9]  János D. Pintér,et al.  Global optimization in action , 1995 .

[10]  B. P. Zhang,et al.  Estimation of the Lipschitz constant of a function , 1996, J. Glob. Optim..

[11]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[12]  Arnold Neumaier,et al.  Global Optimization by Multilevel Coordinate Search , 1999, J. Glob. Optim..

[13]  D. Finkel,et al.  Convergence analysis of the direct algorithm , 2004 .

[14]  Nikolaus Hansen,et al.  The CMA Evolution Strategy: A Comparing Review , 2006, Towards a New Evolutionary Computation.

[15]  M. Ali,et al.  Some Variants of the Controlled Random Search Algorithm for Global Optimization , 2006 .

[16]  Steve Hanneke.  Rates of convergence in active learning , 2011, 1103.1790.

[17]  Adam D. Bull,et al.  Convergence Rates of Efficient Global Optimization Algorithms , 2011, J. Mach. Learn. Res..

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

[19]  Sanjoy Dasgupta,et al.  Two faces of active learning , 2011, Theor. Comput. Sci..

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

[21]  Nikolaos V. Sahinidis,et al.  Derivative-free optimization: a review of algorithms and comparison of software implementations , 2013, J. Glob. Optim..

[22]  Xin-She Yang,et al.  A literature survey of benchmark functions for global optimisation problems , 2013, Int. J. Math. Model. Numer. Optimisation.

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

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

[25]  Ruben Martinez-Cantin,et al.  BayesOpt: a Bayesian optimization library for nonlinear optimization, experimental design and bandits , 2014, J. Mach. Learn. Res..

[26]  Rémi Munos,et al.  Black-box optimization of noisy functions with unknown smoothness , 2015, NIPS.

[27]  Nicolas Vayatis,et al.  A ranking approach to global optimization , 2016, ICML.

[28]  Nikolaus Hansen,et al.  The CMA Evolution Strategy: A Tutorial , 2016, ArXiv.