Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics
DOI10.1214/24-ejp1079arXiv2307.02168MaRDI QIDQ6126984
Fan Chen, Zhenjie Ren, Songbo Wang, Yi-Qing Lin
Publication date: 10 April 2024
Published in: Electronic Journal of Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2307.02168
logarithmic Sobolev inequalityconvergence to equilibriumpropagation of chaoshypocoercivitymean field interactionLangevin diffusion
Asymptotic behavior of solutions to PDEs (35B40) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Diffusion processes (60J60) Hypoelliptic equations (35H10) Dynamical systems and ergodic theory (37-XX) Vlasov equations (35Q83) Fokker-Planck equations (35Q84)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On the rate of convergence in Wasserstein distance of the empirical measure
- Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes
- Quantitative estimates of propagation of chaos for stochastic systems with \(W^{-1,\infty}\) kernels
- Exponential convergence in entropy and Wasserstein for McKean-Vlasov SDEs
- The kinetic Fokker-Planck equation with mean field interaction
- Is there an analog of Nesterov acceleration for gradient-based MCMC?
- Mean-field Langevin dynamics and energy landscape of neural networks
- Convergence rates for the Vlasov-Fokker-Planck equation and uniform in time propagation of chaos in non convex cases
- Propagation of chaos: a review of models, methods and applications. I: Models and methods
- Propagation of chaos: a review of models, methods and applications. II: Applications
- Couplings and quantitative contraction rates for Langevin dynamics
- Long-time behaviour and propagation of chaos for mean field kinetic particles
- Hypocoercivity
- Trend to equilibrium and particle approximation for a weakly selfconsistent Vlasov-Fokker-Planck equation
- A mean field view of the landscape of two-layer neural networks
- Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
- Probabilistic Theory of Mean Field Games with Applications I
- Some methods of speeding up the convergence of iteration methods
- Global-in-time mean-field convergence for singular Riesz-type diffusive flows
This page was built for publication: Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics
