Stein variational gradient descent: many-particle and long-time asymptotics

DOI10.3934/fods.2022023arXiv2102.12956OpenAlexW3131663438MaRDI QIDQ6194470

Nikolas Nüsken, D. R. Michiel Renger

Publication date: 14 February 2024

Published in: Foundations of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.12956

zbMATH Keywords

large deviationsgradient flowsStein variational gradient descent

Mathematics Subject Classification ID

Related Items (1)

Rough McKean-Vlasov dynamics for robust ensemble Kalman filtering

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the relation between gradient flows and the large-deviation principle, with applications to Markov chains and diffusion
• Theory of reproducing kernels and applications
• Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
• Dynamics of labyrinthine pattern formation in magnetic fluids: A mean-field theory
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• On Friedrichs inequality, Helmholtz decomposition, vector potentials, and the div-curl lemma
• A technique for exponential change of measure for Markov processes
• Large deviations for interacting particle systems: joint mean-field and small-noise limit
• The Bayesian update: variational formulations and gradient flows
• Characterisation of gradient flows on finite state Markov chains
• THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
• Second order analysis on (𝒫₂(ℳ),𝒲₂)
• Hilbert space embeddings and metrics on probability measures
• A gradient structure for reaction–diffusion systems and for energy-drift-diffusion systems
• Large Deviations of the Empirical Current in Interacting Particle Systems
• Support Vector Machines
• Handbook of Markov Chain Monte Carlo
• Eulerian Calculus for the Displacement Convexity in the Wasserstein Distance
• Distributions
• The Variational Formulation of the Fokker--Planck Equation
• Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
• Large deviations from the mckean-vlasov limit for weakly interacting diffusions
• Affine Invariant Interacting Langevin Dynamics for Bayesian Inference
• Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler
• Stochastic Processes and Applications
• Data assimilation: The Schrödinger perspective
• Ensemble filter techniques for intermittent data assimilation - a survey
• Eulerian Calculus for the Contraction in the Wasserstein Distance
• Fluctuations and Irreversible Processes
• Optimal Transport

This page was built for publication: Stein variational gradient descent: many-particle and long-time asymptotics