Asymptotics of the spectral gap with applications to the theory of simulated annealing

1989/04/01 by Richard A Holley, Richard A. Holley, Shigeo Kusuoka +2 · 12 citations
Engineering · Computer Science · #Advanced Numerical Analysis Techniques #Advanced Mathematical Modeling in Engineering #Advanced Numerical Methods in Computational Mathematics

paper · doi:10.1016/0022-1236(89)90023-2

Cited by

• Swarm gradient dynamics for global optimization: the mean-field limit case
• Asymptotics of spectral gaps on loop spaces over a class of Riemannian manifolds
• On the convergence of an improved and adaptive kinetic simulated annealing
• Gradient Flow from a Random Walk in Hilbert Space
• Self-concordant Schrödinger operators: spectral gaps and optimization without condition numbers
• Exit event from a metastable state and Eyring-Kramers law for the overdamped Langevin dynamics
• Antithetic variates in higher dimensions
• A consensus-based global optimization method for high dimensional machine learning problems
• Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks
• Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration
• Functional inequalities for Nonlocal Dirichlet Forms With Finite Range Jumps or Large Jumps
• Mean-Field Langevin Diffusions with Density-dependent Temperature