Efficient Batch Black-box Optimization with Deterministic Regret Bounds

In this work, we investigate black-box optimization from the perspective of frequentist kernel methods. We propose a novel batch optimization algorithm, which jointly maximizes the acquisition function and select points from a whole batch in a holistic way. Theoretically, we derive regret bounds for both the noise-free and perturbation settings irrespective of the choice of kernel. Moreover, we analyze the property of the adversarial regret that is required by a robust initialization for Bayesian Optimization (BO). We prove that the adversarial regret bounds decrease with the decrease of covering radius, which provides a criterion for generating a point set to minimize the bound. We then propose fast searching algorithms to generate a point set with a small covering radius for the robust initialization. Experimental results on both synthetic benchmark problems and real-world problems show the effectiveness of the proposed algorithms.

[1]  Zi Wang,et al.  Batched Large-scale Bayesian Optimization in High-dimensional Spaces , 2017, AISTATS.

[2]  R. Caflisch.  Monte Carlo and quasi-Monte Carlo methods , 1998, Acta Numerica.

[3]  Andreas Krause,et al.  No-regret Bayesian Optimization with Unknown Hyperparameters , 2019, J. Mach. Learn. Res..

[4]  Peter I. Frazier,et al.  The Parallel Knowledge Gradient Method for Batch Bayesian Optimization , 2016, NIPS.

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

[6]  M. Urner.  Scattered Data Approximation , 2016 .

[7]  Philipp Hennig,et al.  Entropy Search for Information-Efficient Global Optimization , 2011, J. Mach. Learn. Res..

[8]  Andreas Krause,et al.  Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation , 2016, NIPS.

[9]  H. Keng,et al.  Applications of number theory to numerical analysis , 1981 .

[10]  Nicolas Vayatis,et al.  Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Exploration , 2013, ECML/PKDD.

[12]  Rémi Munos,et al.  Pure Exploration in Multi-armed Bandits Problems , 2009, ALT.

[13]  Jonathan Scarlett,et al.  Tight Regret Bounds for Bayesian Optimization in One Dimension , 2018, ICML.

[14]  Zi Wang,et al.  Max-value Entropy Search for Efficient Bayesian Optimization , 2017, ICML.

[15]  Thomas Bäck,et al.  A Survey of Evolution Strategies , 1991, ICGA.

[16]  Zoubin Ghahramani,et al.  Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions , 2015, NIPS.

[17]  Stefan M. Wild,et al.  Derivative-free optimization methods , 2019, Acta Numerica.

[18]  Harold J. Kushner,et al.  A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise , 1964 .

[19]  Matthew W. Hoffman,et al.  Predictive Entropy Search for Efficient Global Optimization of Black-box Functions , 2014, NIPS.

[20]  Petros Koumoutsakos,et al.  Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES) , 2003, Evolutionary Computation.

[21]  Dino Sejdinovic,et al.  Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences , 2018, ArXiv.

[22]  Charles Audet,et al.  Derivative-Free and Blackbox Optimization , 2017 .

[23]  G. Gary Wang,et al.  Review of Metamodeling Techniques in Support of Engineering Design Optimization , 2007, DAC 2006.

[24]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[25]  Tao Wang,et al.  Automatic Gait Optimization with Gaussian Process Regression , 2007, IJCAI.

[26]  Alan Fern,et al.  Using trajectory data to improve bayesian optimization for reinforcement learning , 2014, J. Mach. Learn. Res..

[27]  Warren B. Powell,et al.  The Knowledge-Gradient Algorithm for Sequencing Experiments in Drug Discovery , 2011, INFORMS J. Comput..

[28]  Lalit M. Patnaik,et al.  Genetic algorithms: a survey , 1994, Computer.

[29]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

[30]  Jonas Mockus,et al.  On Bayesian Methods for Seeking the Extremum , 1974, Optimization Techniques.

[31]  Volkan Cevher,et al.  Adversarially Robust Optimization with Gaussian Processes , 2018, NeurIPS.

[32]  Warren B. Powell,et al.  The Knowledge-Gradient Policy for Correlated Normal Beliefs , 2009, INFORMS J. Comput..

[33]  Alexander Keller,et al.  ( t, m, s )-Nets and Maximized Minimum Distance , 2008 .

[34]  Yurii Nesterov,et al.  Random Gradient-Free Minimization of Convex Functions , 2015, Foundations of Computational Mathematics.

[35]  Neil D. Lawrence,et al.  Batch Bayesian Optimization via Local Penalization , 2015, AISTATS.

[36]  Yueming Lyu,et al.  Spherical Structured Feature Maps for Kernel Approximation , 2017, ICML.

[37]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[38]  S. Dammertz,et al.  Image Synthesis by Rank-1 Lattices , 2008 .

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

[40]  Peter Auer,et al.  Using Confidence Bounds for Exploitation-Exploration Trade-offs , 2003, J. Mach. Learn. Res..

[41]  Andreas Krause,et al.  Parallelizing Exploration-Exploitation Tradeoffs with Gaussian Process Bandit Optimization , 2012, ICML.

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