Stochastic optimization on continuous domains with finite-time guarantees by Markov chain Monte Carlo methods

Abstract

We introduce bounds on the finite-time performance of Markov chain Monte Carlo algorithms in approaching the global solution of stochastic optimization problems over continuous domains. A comparison with other state-of-the-art methods having finite-time guarantees for solving stochastic programming problems is included.

29 pages, 6 figures. Revised version based on referees report

References in corpus (3)

• General state space Markov chains and MCMC algorithms
• Stochastic optimization on continuous domains with finite-time guarantees by Markov chain Monte Carlo methods
• Simulated Annealing: Rigorous finite-time guarantees for optimization on continuous domains

Cited by in corpus (5)

• Performance Bounds for the Scenario Approach and an Extension to a Class of Non-convex Programs
• Stochastic optimization on continuous domains with finite-time guarantees by Markov chain Monte Carlo methods
• Conformance Testing as Falsification for Cyber-Physical Systems
• On the computational complexity and generalization properties of multi-stage and recursive scenario programs
• Unbounded-Time Safety Verification of Stochastic Differential Dynamics