Title :
Gradient-Based Adaptive Stochastic Search for Non-Differentiable Optimization
Author :
Enlu Zhou ; Jiaqiao Hu
Author_Institution :
Stewart Sch. of Ind. & Syst. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
In this paper, we propose a stochastic search algorithm for solving general optimization problems with little structure. The algorithm iteratively finds high quality solutions by randomly sampling candidate solutions from a parameterized distribution model over the solution space. The basic idea is to convert the original (possibly non-differentiable) problem into a differentiable optimization problem on the parameter space of the parameterized sampling distribution, and then use a direct gradient search method to find improved sampling distributions. Thus, the algorithm combines the robustness feature of stochastic search from considering a population of candidate solutions with the relative fast convergence speed of classical gradient methods by exploiting local differentiable structures. We analyze the convergence and converge rate properties of the proposed algorithm, and carry out numerical study to illustrate its performance.
Keywords :
approximation theory; convergence; gradient methods; sampling methods; search problems; stochastic programming; candidate solution sampling; converge rate property; differentiable optimization problem; direct gradient search method; general optimization problems; gradient-based adaptive stochastic search; local differentiable structures; nondifferentiable optimization; numerical study; parameter space; parameterized distribution model; parameterized sampling distribution; stochastic approximation; Aerospace electronics; Approximation algorithms; Approximation methods; Convergence; Optimization; Reactive power; Stochastic processes; Stochastic approximation; black-box optimization; stochastic search;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.2014.2310052