Essential barrier height and a probabilistic approach in characterizing potential landscape

DOI10.1016/J.SPA.2025.104763MaRDI QIDQ6910591zbMATH OpenFDO

Authors Yao Li, Molei Tao, Shirou Wang

Publication date 29 October 2025

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.SPA.2025.104763

zbMATH Keywords

coupling methodessential barrier heightnon-convexityoverdamped Langevin dynamicspotential landscape

Mathematics Subject Classification ID

Generation, random and stochastic difference and differential equations (37H10) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Computational methods in Markov chains (60J22) Diffusion processes (60J60)

Cites work

• A correction note on the first passage time of an Ornstein-Uhlenbeck process to a boundary
• A mean field view of the landscape of two-layer neural networks
• Can One Hear the Shape of a Drum?
• Coupling methods for multidimensional diffusion processes
• Coupling of multidimensional diffusions by reflection
• Couplings and quantitative contraction rates for Langevin dynamics
• Entropy Bounds for Discrete Random Variables via Maximal Coupling
• Every Local Minimum Value Is the Global Minimum Value of Induced Model in Nonconvex Machine Learning
• Exact approximation rate of killed hypoelliptic diffusions using the discrete Euler scheme
• Geometric ergodicity of Harris recurrent Markov chains with applications to renewal theory
• Global minima of overparameterized neural networks
• scientific article; zbMATH DE number 3812655 (Why is no real title available?)
• scientific article; zbMATH DE number 1239549 (Why is no real title available?)
• scientific article; zbMATH DE number 1834589 (Why is no real title available?)
• scientific article; zbMATH DE number 3035137 (Why is no real title available?)
• Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
• Mean field analysis of neural networks: a central limit theorem
• Metastability in reversible diffusion processes. I: Sharp asymptotics for capacities and exit times
• Metastability in reversible diffusion processes. II: Precise asymptotics for small eigenvalues
• Noisy heteroclinic networks
• Normal forms approach to diffusion near hyperbolic equilibria
• Numerical computations of geometric ergodicity for stochastic dynamics
• On the exponential exit law in the small parameter exit problem
• Quantitative contraction rates for Markov chains on general state spaces
• Stopped diffusion processes: boundary corrections and overshoot
• The Evaluation of Matrix Inversion Programs
• Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks

This page was built for publication: Essential barrier height and a probabilistic approach in characterizing potential landscape

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6910591)