Simulated Annealing In $\mathbf{R}^d$ With Slowly Growing Potentials
Nicolas Fournier, Pierre Monmarch\'e, Camille Tardif

TL;DR
This paper investigates the behavior of continuous-time simulated annealing in high-dimensional spaces with slowly growing potentials, identifying a phase transition at potentials growing like a double logarithm.
Contribution
It weakens previous growth assumptions for potentials in simulated annealing and characterizes the transition point for potentials growing like a double logarithm.
Findings
Transition occurs at potentials growing like a log log |x|
Applicable to potentials with unbounded local minima
Extends previous results with weaker growth conditions
Abstract
We use a localization procedure to weaken the growth assumptions of Royer [8], Miclo [4] and Zitt [9] concerning the continuous-time simulated annealing in . We show that a transition occurs for potentials growing like at infinity. We also study a class of potentials with possibly unbounded sets of local minima.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStochastic processes and statistical mechanics · Markov Chains and Monte Carlo Methods · Stochastic processes and financial applications
