Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler

DOI10.1137/19M1251655zbMath1447.65119arXiv1903.08866OpenAlexW3005085468MaRDI QIDQ5109769

Franca Hoffmann, Wuchen Li, Andrew M. Stuart, Alfredo Garbuno-Inigo

Publication date: 13 May 2020

Published in: SIAM Journal on Applied Dynamical Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1903.08866

zbMATH Keywords

gradient flowensemble Kalman inversionmean-field Fokker-Planck equationKalman-Wasserstein metric

Mathematics Subject Classification ID

Bayesian inference (62F15) Numerical computation of solutions to systems of equations (65H10) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31) PDEs with randomness, stochastic partial differential equations (35R60) Numerical solutions to stochastic differential and integral equations (65C30) Numerical methods for inverse problems for boundary value problems involving PDEs (65N21) Stochastic particle methods (65C35) Fokker-Planck equations (35Q84) Stochastic analysis in statistical mechanics (82M60)

Related Items (58)

Projected Wasserstein Gradient Descent for High-Dimensional Bayesian Inference ⋮ Semi-discrete optimization through semi-discrete optimal transport: a framework for neural architecture search ⋮ Constrained Consensus-Based Optimization ⋮ Calibrate, emulate, sample ⋮ Derivative-Free Bayesian Inversion Using Multiscale Dynamics ⋮ Continuous Time Limit of the Stochastic Ensemble Kalman Inversion: Strong Convergence Analysis ⋮ GP-ETAS: semiparametric Bayesian inference for the spatio-temporal epidemic type aftershock sequence model ⋮ Generalized unnormalized optimal transport and its fast algorithms ⋮ Efficient derivative-free Bayesian inference for large-scale inverse problems ⋮ Particle dual averaging: optimization of mean field neural network with global convergence rate analysis* ⋮ Recent trends on nonlinear filtering for inverse problems ⋮ Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion ⋮ Constrained ensemble Langevin Monte Carlo ⋮ Computational mean-field information dynamics associated with reaction-diffusion equations ⋮ Convergence acceleration of ensemble Kalman inversion in nonlinear settings ⋮ A Stabilization of a Continuous Limit of the Ensemble Kalman Inversion ⋮ Ensemble Inference Methods for Models With Noisy and Expensive Likelihoods ⋮ On a Metropolis-Hastings importance sampling estimator ⋮ Iterated Kalman methodology for inverse problems ⋮ Ensemble Markov Chain Monte Carlo with Teleporting Walkers ⋮ Birth–death dynamics for sampling: global convergence, approximations and their asymptotics ⋮ Stein Variational Gradient Descent on Infinite-Dimensional Space and Applications to Statistical Inverse Problems ⋮ Global Optimization via Schrödinger–Föllmer Diffusion ⋮ Consensus‐based sampling ⋮ Component-wise iterative ensemble Kalman inversion for static Bayesian models with unknown measurement error covariance ⋮ Exponential entropy dissipation for weakly self-consistent Vlasov-Fokker-Planck equations ⋮ High order spatial discretization for variational time implicit schemes: Wasserstein gradient flows and reaction-diffusion systems ⋮ Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks ⋮ Complete Deterministic Dynamics and Spectral Decomposition of the Linear Ensemble Kalman Inversion ⋮ Adaptive Ensemble Kalman Inversion with Statistical Linearization ⋮ Surrogate modeling for Bayesian inverse problems based on physics-informed neural networks ⋮ Tikhonov Regularization within Ensemble Kalman Inversion ⋮ Filtering Methods for Coupled Inverse Problems ⋮ Subsampling in ensemble Kalman inversion ⋮ Bayesian spatiotemporal modeling for inverse problems ⋮ Ensemble-Based Gradient Inference for Particle Methods in Optimization and Sampling ⋮ Stein variational gradient descent: many-particle and long-time asymptotics ⋮ Affine-invariant ensemble transform methods for logistic regression ⋮ Adaptive regularisation for ensemble Kalman inversion ⋮ Gradient-free Stein variational gradient descent with kernel approximation ⋮ Unnamed Item ⋮ Stein variational gradient descent with local approximations ⋮ Ensemble Kalman inversion: mean-field limit and convergence analysis ⋮ Affine Invariant Interacting Langevin Dynamics for Bayesian Inference ⋮ Discrete gradients for computational Bayesian inference ⋮ Accelerated information gradient flow ⋮ Ensemble slice sampling. Parallel, black-box and gradient-free inference for correlated \& multimodal distributions ⋮ Wasserstein stability estimates for covariance-preconditioned Fokker–Planck equations ⋮ Iterative ensemble Kalman methods: a unified perspective with some new variants ⋮ Ensemble Kalman inversion for nonlinear problems: weights, consistency, and variance bounds ⋮ Fokker--Planck Particle Systems for Bayesian Inference: Computational Approaches ⋮ Ensemble Kalman inversion for sparse learning of dynamical systems from time-averaged data ⋮ Error Analysis for Probabilities of Rare Events with Approximate Models ⋮ Propagation of chaos: a review of models, methods and applications. II: Applications ⋮ Ensemble Kalman Sampler: Mean-field Limit and Convergence Analysis ⋮ Hessian metric via transport information geometry ⋮ The Ensemble Kalman Filter for Rare Event Estimation ⋮ Gradient flow structure and convergence analysis of the ensemble Kalman inversion for nonlinear forward models

Uses Software

• EnKF
• EnsembleQN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Ensemble samplers with affine invariance
• Variance reduction using nonreversible Langevin samplers
• Diffusion limits of the random walk Metropolis algorithm in high dimensions
• Noisy gradient flow from a random walk in Hilbert space
• A dynamical systems framework for intermittent data assimilation
• Bayesian inference with optimal maps
• Kinetic models of opinion formation
• Iterative regularization for ensemble data assimilation in reservoir models
• From particle to kinetic and hydrodynamic descriptions of flocking
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Optimal scaling for various Metropolis-Hastings algorithms.
• On the stability and the uniform propagation of chaos properties of ensemble Kalman-Bucy filters
• Ensemble preconditioning for Markov chain Monte Carlo simulation
• Investigation of the sampling performance of ensemble-based methods with a simple reservoir model
• Natural gradient via optimal transport
• Statistical and computational inverse problems.
• Online natural gradient as a Kalman filter
• Wasserstein proximal of GANs
• Optimal scaling of random-walk Metropolis algorithms on general target distributions
• Discrete gradients for computational Bayesian inference
• Affine natural proximal learning
• Kinetic methods for inverse problems
• A gentle stochastic thermostat for molecular dynamics
• Weak convergence of Metropolis algorithms for non-I.I.D. target distributions
• Optimal acceptance rates for Metropolis algorithms: Moving beyond 0.234
• Time integration and discrete Hamiltonian systems
• ON CONVEX SOBOLEV INEQUALITIES AND THE RATE OF CONVERGENCE TO EQUILIBRIUM FOR FOKKER-PLANCK TYPE EQUATIONS
• THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
• A regularizing iterative ensemble Kalman method for PDE-constrained inverse problems
• Ensemble Kalman methods for inverse problems
• A Nonparametric Ensemble Transform Method for Bayesian Inference
• Well-posedness and accuracy of the ensemble Kalman filter in discrete and continuous time
• On the Stability and the Uniform Propagation of Chaos of a Class of Extended Ensemble Kalman--Bucy Filters
• Asymptotic analysis for the generalized Langevin equation
• Particle, kinetic, and hydrodynamic models of swarming
• Long-Time Stability and Accuracy of the Ensemble Kalman--Bucy Filter for Fully Observed Processes and Small Measurement Noise
• Analysis of the Ensemble and Polynomial Chaos Kalman Filters in Bayesian Inverse Problems
• Approximate McKean–Vlasov representations for a class of SPDEs
• Optimal scaling of Metropolis algorithms: Heading toward general target distributions
• The Density Manifold and Configuration Space Quantization
• Exponential convergence toward equilibrium for homogeneous Fokker-Planck-type equations
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Geometric integration using discrete gradients
• Runge–Kutta Methods for Dissipative and Gradient Dynamical Systems
• The Variational Formulation of the Fokker--Planck Equation
• Reciprocal Relations in Irreversible Processes. I.
• Reciprocal Relations in Irreversible Processes. II.
• An analytical framework for consensus-based global optimization method
• Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Convergence analysis of ensemble Kalman inversion: the linear, noisy case
• Bayesian Measures of Model Complexity and Fit
• Tikhonov Regularization within Ensemble Kalman Inversion
• Stochastic Processes and Applications
• Probabilistic Forecasting and Bayesian Data Assimilation
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Poisson's Equation in Nonlinear Filtering
• Data Assimilation
• Analysis of the Ensemble Kalman Filter for Inverse Problems
• Information Geometry
• Feedback Particle Filter
• The ensemble Kalman filter for combined state and parameter estimation
• Filtering Complex Turbulent Systems
• Energy-diminishing integration of gradient systems
• Fluctuations and Irreversible Process. II. Systems with Kinetic Energy
• Optimal Transport
• MCMC methods for functions: modifying old algorithms to make them faster

This page was built for publication: Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler