State-Dependent Temperature Control for Langevin Diffusions

DOI10.1137/21M1429424zbMath1493.93057arXiv2011.07456MaRDI QIDQ5080490

Zuo Quan Xu, Xuefeng Gao, Xun Yu Zhou

Publication date: 31 May 2022

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.07456

zbMATH Keywords

nonconvex optimizationHJB equationLangevin diffusionentropy regularizationstochastic relaxed controlBoltzmann exploration

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Optimal stochastic control (93E20) Existence of optimal solutions belonging to restricted classes (Lipschitz controls, bang-bang controls, etc.) (49J30)

Related Items

Exploratory HJB Equations and Their Convergence, Choquet Regularization for Continuous-Time Reinforcement Learning, Tail probability estimates of continuous-time simulated annealing processes, Exploratory Control with Tsallis Entropy for Latent Factor Models

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimization by Simulated Annealing
• Asymptotics of the spectral gap with applications to the theory of simulated annealing
• Convergence rates for annealing diffusion processes
• Metastability in reversible diffusion processes. I: Sharp asymptotics for capacities and exit times
• Metastability in reversible diffusion processes. II: Precise asymptotics for small eigenvalues
• An improved annealing method and its large-time behavior
• Weight-preserving simulated tempering
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Diffusions for Global Optimization
• Diffusion for Global Optimization in $\mathbb{R}^n $
• Recursive Stochastic Algorithms for Global Optimization in $\mathbb{R}^d $
• Solving high-dimensional partial differential equations using deep learning
• Smooth Regularization of Bang-Bang Optimal Control Problems
• Diffusion processes with continuous coefficients, I
• New smoothing techniques for solving bang–bang optimal control problems—numerical results and statistical interpretation