On the fast convergence of random perturbations of the gradient flow

DOI10.3233/ASY-201622zbMath1473.35542arXiv1706.00837OpenAlexW3029830352MaRDI QIDQ5000006

Chris Junchi Li, Wenqing Hu, Jiao-Jiao Yang

Publication date: 5 July 2021

Published in: Asymptotic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1706.00837

zbMATH Keywords

diffusion approximationsaddle pointexit problemstochastic gradient descentrandom perturbations of dynamical systems

Mathematics Subject Classification ID

Perturbations in context of PDEs (35B20) PDEs with randomness, stochastic partial differential equations (35R60) Gradient-like behavior; isolated (locally maximal) invariant sets; attractors, repellers for topological dynamical systems (37B35) Critical points of functionals in context of PDEs (e.g., energy functionals) (35B38) PDEs in connection with computer science (35Q68)

Related Items (1)

Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Noisy heteroclinic networks
• Nonconvergence to unstable points in urn models and stochastic approximations
• The exit problem for small random perturbations of dynamical systems with a hyperbolic fixed point
• On the diffusion approximation of nonconvex stochastic gradient descent
• Random perturbations of 2-dimensional Hamiltonian flows
• Exit asymptotics for small diffusion about an unstable equilibrium
• Normal forms approach to diffusion near hyperbolic equilibria
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Morse Theory. (AM-51)
• Stochastic Gradient Descent in Continuous Time
• Introduction to Dynamical Systems
• A new method of extension of local maps of Banach spaces. Applications and examples
• A Stochastic Approximation Method

This page was built for publication: On the fast convergence of random perturbations of the gradient flow