Global Optimization for Stochastic Programming Via Sequential Monte Carlo Sampling

This paper proposes a continuous-time optimization algorithm for stochastic programming. We introduce the sequential Monte Carlo sampling scheme to do with the high dimensionality of the stochastic disturbance and the switching gradient Lagevin dynamics to reduce the computational requirement on evaluation of the gradient on large data set. Our algorithm is in continuous-time and can seek the global minimizer of stochastic programming problems. We fit our analysis into the framework of two-time-scale systems and propose a stochastic averaging approach to analyze the convergence of our optimization algorithm. With the help of Dirichlet form, Fredholm alternative and Poincare inequality and by means of the tool of Fokker-Planck equation, we provide a rigorous theoretical foundation for the analysis and design of the global optimization algorithm. The importance of our algorithm on the one hand stems from serving the application-oriented purpose such as dealing with high-dimensionality and reducing computational complexity, and on the other hand originates in providing some theoretically interesting techniques which is of direct applicability for global optimization problems.

[1]  Jessika Eichel,et al.  Partial Differential Equations Second Edition , 2016 .

[2]  Xiaoli Wang,et al.  Averaging approach to distributed convex optimization for continuous-time multi-agent systems , 2017, Kybernetika.

[3]  Xiaoli Wang,et al.  Leader-following consensus of multiple linear systems under switching topologies: an averaging method , 2012, Kybernetika.

[4]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

[5]  G. Pavliotis.  Stochastic Processes and Applications: Diffusion Processes, the Fokker-Planck and Langevin Equations , 2014 .

[6]  Jason Brownlee,et al.  Clever Algorithms: Nature-Inspired Programming Recipes , 2012 .

[7]  C. J. Price,et al.  A cover partitioning method for bound constrained global optimization , 2012, Optim. Methods Softw..

[8]  E. Lieb,et al.  On extensions of the Brunn-Minkowski and Prékopa-Leindler theorems, including inequalities for log concave functions, and with an application to the diffusion equation , 1976 .

[9]  Emile H. L. Aarts,et al.  Global optimization and simulated annealing , 1991, Math. Program..

[10]  Alexander Shapiro,et al.  The empirical behavior of sampling methods for stochastic programming , 2006, Ann. Oper. Res..

[11]  Grigorios A. Pavliotis,et al.  Multiscale Methods: Averaging and Homogenization , 2008 .

[12]  M. E. Johnson,et al.  Generalized simulated annealing for function optimization , 1986 .

[13]  Xiaoli Wang,et al.  Consensus controllability, observability and robust design for leader-following linear multi-agent systems , 2013, Autom..

[14]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[15]  John Holland,et al.  Adaptation in Natural and Artificial Sys-tems: An Introductory Analysis with Applications to Biology , 1975 .

[16]  M. J. Appel,et al.  On Accelerated Random Search , 2003, SIAM J. Optim..

[17]  R. Tweedie,et al.  Exponential convergence of Langevin distributions and their discrete approximations , 1996 .

[18]  Sandro Ridella,et al.  Minimizing multimodal functions of continuous variables with the “simulated annealing” algorithmCorrigenda for this article is available here , 1987, TOMS.

[19]  C. Hwang,et al.  Diffusion for global optimization in R n , 1987 .

[20]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[21]  Alexander Shapiro,et al.  On the Rate of Convergence of Optimal Solutions of Monte Carlo Approximations of Stochastic Programs , 2000, SIAM J. Optim..

[22]  James Smith,et al.  A tutorial for competent memetic algorithms: model, taxonomy, and design issues , 2005, IEEE Transactions on Evolutionary Computation.

[23]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[24]  Dongya Zhao,et al.  Stochastic averaging approach to leader-following consensus of linear multi-agent systems , 2016, J. Frankl. Inst..