Multi-Objective Simultaneous Optimistic Optimization

Optimistic methods have been applied with success to single-objective optimization. Here, we attempt to bridge the gap between optimistic methods and multi-objective optimization. In particular, this paper is concerned with solving black-box multi-objective problems given a finite number of function evaluations and proposes an optimistic approach, which we refer to as the Multi-Objective Simultaneous Optimistic Optimization (MO-SOO). Popularized by multi-armed bandits, MO-SOO follows the optimism in the face of uncertainty principle to recognize Pareto optimal solutions, by combining several multi-armed bandits in a hierarchical structure over the feasible decision space of a multi-objective problem. Based on three assumptions about the objective functions smoothness and hierarchical partitioning, the algorithm finite-time and asymptotic convergence behaviors are analyzed. The finite-time analysis establishes an upper bound on the Pareto-compliant unary additive epsilon indicator characterized by the objectives smoothness as well as the structure of the Pareto front with respect to its extrema. On the other hand, the asymptotic analysis indicates the consistency property of MO-SOO. Moreover, we validate the theoretical provable performance of the algorithm on a set of synthetic problems. Finally, three-hundred bi-objective benchmark problems from the literature are used to substantiate the performance of the optimistic approach and compare it with three state-of-the-art stochastic algorithms, namely MOEA/D, MO-CMA-ES, and SMS-EMOA in terms of two Pareto-compliant quality indicators. Besides sound theoretical properties, MO-SOO shows a performance on a par with the top performing stochastic algorithm, viz. SMS-EMOA.

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

[2]  Lothar Thiele,et al.  A Tutorial on the Performance Assessment of Stochastic Multiobjective Optimizers , 2006 .

[3]  J D Pinter,et al.  Global Optimization in Action—Continuous and Lipschitz Optimization: Algorithms, Implementations and Applications , 2010 .

[4]  Sylvain Gelly,et al.  Modifications of UCT and sequence-like simulations for Monte-Carlo Go , 2007, 2007 IEEE Symposium on Computational Intelligence and Games.

[5]  Abdullah Al-Dujaili,et al.  A MATLAB Toolbox for Surrogate-Assisted Multi-Objective Optimization: A Preliminary Study , 2016, GECCO.

[6]  Csaba Szepesvári,et al.  Multi-criteria Reinforcement Learning , 1998, ICML.

[7]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[8]  Shimon Whiteson,et al.  A Survey of Multi-Objective Sequential Decision-Making , 2013, J. Artif. Intell. Res..

[9]  John N. Tsitsiklis,et al.  Linearly Parameterized Bandits , 2008, Math. Oper. Res..

[10]  Peter Vrancx,et al.  Multi-objective χ-Armed bandits , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

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

[12]  Ching-Lai Hwang,et al.  Fuzzy Multiple Attribute Decision Making - Methods and Applications , 1992, Lecture Notes in Economics and Mathematical Systems.

[13]  Sundaram Suresh,et al.  Dividing rectangles attack multi-objective optimization , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[14]  Nando de Freitas,et al.  Bayesian Multi-Scale Optimistic Optimization , 2014, AISTATS.

[15]  Ann Nowé,et al.  Designing multi-objective multi-armed bandits algorithms: A study , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[16]  Abdullah Al-Dujaili,et al.  Multi-Objective Self Regulating Particle Swarm Optimization algorithm for BMOBench platform , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

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

[18]  Yaroslav D. Sergeyev,et al.  Derivative-Free Local Tuning and Local Improvement Techniques Embedded in the Univariate Global Optimization , 2016, J. Optim. Theory Appl..

[19]  Abdullah Al-Dujaili,et al.  Hypervolume-Based DIRECT for Multi-Objective Optimisation , 2016, GECCO.

[20]  Sriraam Natarajan,et al.  Dynamic preferences in multi-criteria reinforcement learning , 2005, ICML.

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

[22]  H. Robbins Some aspects of the sequential design of experiments , 1952 .

[23]  Robert Michael Lewis,et al.  A Globally Convergent Augmented Lagrangian Pattern Search Algorithm for Optimization with General Constraints and Simple Bounds , 2002, SIAM J. Optim..

[24]  Alex Y. D. Siem,et al.  Derivative-free generation and interpolation of convex Pareto optimal IMRT plans , 2006, Physics in medicine and biology.

[25]  Katya Scheinberg,et al.  Global Convergence of General Derivative-Free Trust-Region Algorithms to First- and Second-Order Critical Points , 2009, SIAM J. Optim..

[26]  Shie Mannor,et al.  A Geometric Approach to Multi-Criterion Reinforcement Learning , 2004, J. Mach. Learn. Res..

[27]  Rajeev Kumar,et al.  Running Time Analysis of a Multiobjective Evolutionary Algorithm on Simple and Hard Problems , 2005, FOGA.

[28]  Aimo A. Törn,et al.  Global Optimization , 1999, Science.

[29]  Q. Henry Wu,et al.  Multi-objective optimization by reinforcement learning for power system dispatch and voltage stability , 2010, 2010 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe).

[30]  R. K. Ursem Multi-objective Optimization using Evolutionary Algorithms , 2009 .

[31]  Nicola Beume,et al.  SMS-EMOA: Multiobjective selection based on dominated hypervolume , 2007, Eur. J. Oper. Res..

[32]  Jan Swevers,et al.  Iterative optimization of the filling phase of wet clutches , 2010, 2010 11th IEEE International Workshop on Advanced Motion Control (AMC).

[33]  Qingfu Zhang,et al.  Adaptive Operator Selection With Bandits for a Multiobjective Evolutionary Algorithm Based on Decomposition , 2014, IEEE Transactions on Evolutionary Computation.

[34]  Marco Laumanns,et al.  SPEA2: Improving the Strength Pareto Evolutionary Algorithm For Multiobjective Optimization , 2002 .

[35]  Günter Rudolph,et al.  Evolutionary Search for Minimal Elements in Partially Ordered Finite Sets , 1998, Evolutionary Programming.

[36]  Evan Dekker,et al.  Empirical evaluation methods for multiobjective reinforcement learning algorithms , 2011, Machine Learning.

[37]  Sundaram Suresh,et al.  A Naive multi-scale search algorithm for global optimization problems , 2016, Inf. Sci..

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

[39]  C. Hwang Multiple Objective Decision Making - Methods and Applications: A State-of-the-Art Survey , 1979 .

[40]  Ilya Loshchilov,et al.  Surrogate-Assisted Evolutionary Algorithms , 2013 .

[41]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.

[42]  Marco Laumanns,et al.  Performance assessment of multiobjective optimizers: an analysis and review , 2003, IEEE Trans. Evol. Comput..

[43]  Christian Igel,et al.  Improved step size adaptation for the MO-CMA-ES , 2010, GECCO '10.

[44]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[45]  Carl Tim Kelley,et al.  Iterative methods for optimization , 1999, Frontiers in applied mathematics.

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

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

[48]  Michèle Sebag,et al.  Multi-objective Monte-Carlo Tree Search , 2012, ACML.

[49]  W. R. Thompson ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES , 1933 .

[50]  Charles Audet,et al.  Mesh Adaptive Direct Search Algorithms for Constrained Optimization , 2006, SIAM J. Optim..

[51]  V. Pareto Manual of Political Economy: A Critical and Variorum Edition , 2014 .

[52]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[53]  J. F. Aguilar Madeira,et al.  Surgical correction of scoliosis: numerical analysis and optimization of the procedure , 2010 .

[54]  Dimo Brockhoff,et al.  Benchmarking Numerical Multiobjective Optimizers Revisited , 2015, GECCO.

[55]  Srini Narayanan,et al.  Learning all optimal policies with multiple criteria , 2008, ICML '08.

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

[57]  Csaba Szepesvári,et al.  Online Optimization in X-Armed Bandits , 2008, NIPS.

[58]  Thomas Hanne,et al.  On the convergence of multiobjective evolutionary algorithms , 1999, Eur. J. Oper. Res..

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

[60]  Y. Sergeyev On convergence of "divide the best" global optimization algorithms , 1998 .

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

[62]  C. T. Kelley,et al.  Modifications of the direct algorithm , 2001 .

[63]  Luís N. Vicente,et al.  Direct Multisearch for Multiobjective Optimization , 2011, SIAM J. Optim..

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

[65]  Katya Scheinberg,et al.  On the convergence of derivative-free methods for unconstrained optimization , 1997 .