Lecchini-Visintini, A and Lygeros, J and Maciejowski, J Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains. (Unpublished)Full text not available from this repository.
Simulated annealing is a popular method for approaching the solution of a global optimization problem. Existing results on its performance apply to discrete combinatorial optimization where the optimization variables can assume only a finite set of possible values. We introduce a new general formulation of simulated annealing which allows one to guarantee finite-time performance in the optimization of functions of continuous variables. The results hold universally for any optimization problem on a bounded domain and establish a connection between simulated annealing and up-to-date theory of convergence of Markov chain Monte Carlo methods on continuous domains. This work is inspired by the concept of finite-time learning with known accuracy and confidence developed in statistical learning theory.
|Uncontrolled Keywords:||stat.ML stat.ML|
|Divisions:||Div F > Control|
|Depositing User:||Unnamed user with email firstname.lastname@example.org|
|Date Deposited:||15 Dec 2015 13:10|
|Last Modified:||01 May 2016 23:02|