Convergence rate of a simulated annealing algorithm with noisy observations
Machine Learning
2017-03-02 v1 Optimization and Control
Statistics Theory
Statistics Theory
Abstract
In this paper we propose a modified version of the simulated annealing algorithm for solving a stochastic global optimization problem. More precisely, we address the problem of finding a global minimizer of a function with noisy evaluations. We provide a rate of convergence and its optimized parametrization to ensure a minimal number of evaluations for a given accuracy and a confidence level close to 1. This work is completed with a set of numerical experimentations and assesses the practical performance both on benchmark test cases and on real world examples.
Cite
@article{arxiv.1703.00329,
title = {Convergence rate of a simulated annealing algorithm with noisy observations},
author = {Clément Bouttier and Ioana Gavra},
journal= {arXiv preprint arXiv:1703.00329},
year = {2017}
}