Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains

Details Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains

2007-09-19

arxiv.org/abs/0709.2989v1

Statistics

Machine Learning

10 pages, 2 figures. Preprint. The final version will appear in: Advances in Neural Information Processing Systems 20, Proceed

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-336568