A stochastic version of Stein variational gradient descent for efficient sampling
From MaRDI portal
Abstract: We propose in this work RBM-SVGD, a stochastic version of Stein Variational Gradient Descent (SVGD) method for efficiently sampling from a given probability measure and thus useful for Bayesian inference. The method is to apply the Random Batch Method (RBM) for interacting particle systems proposed by Jin et al to the interacting particle systems in SVGD. While keeping the behaviors of SVGD, it reduces the computational cost, especially when the interacting kernel has long range. Numerical examples verify the efficiency of this new version of SVGD.
Recommendations
- Stein variational gradient descent with local approximations
- Stein variational gradient descent on infinite-dimensional space and applications to statistical inverse problems
- Stein variational reduced basis Bayesian inversion
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- Stochastic gradient Hamiltonian Monte Carlo with variance reduction for Bayesian inference
Cites work
- A Stochastic Approximation Method
- Adaptive subgradient methods for online learning and stochastic optimization
- Data Assimilation
- scientific article; zbMATH DE number 3174732 (Why is no real title available?)
- scientific article; zbMATH DE number 2012512 (Why is no real title available?)
- scientific article; zbMATH DE number 1569102 (Why is no real title available?)
- Monte Carlo sampling methods using Markov chains and their applications
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- Random batch methods (RBM) for interacting particle systems
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- Theory of Reproducing Kernels
Cited in
(25)- Particle-based energetic variational inference
- On the mean field limit of the random batch method for interacting particle systems
- Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories
- Gradient-free Stein variational gradient descent with kernel approximation
- Stein variational gradient descent with local approximations
- Random-batch method for multi-species stochastic interacting particle systems
- Stein's method meets computational statistics: a review of some recent developments
- Batched Stochastic Gradient Descent with Weighted Sampling
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- A Random Batch Ewald Method for Particle Systems with Coulomb Interactions
- Random Batch Methods for Classical and Quantum Interacting Particle Systems and Statistical Samplings
- Random Batch Particle Methods for the Homogeneous Landau Equation
- Some random batch particle methods for the Poisson-Nernst-Planck and Poisson-Boltzmann equations
- On the random batch method for second order interacting particle systems
- Stein variational gradient descent on infinite-dimensional space and applications to statistical inverse problems
- A Random-Batch Monte Carlo Method for Many-Body Systems with Singular Kernels
- Random batch algorithms for quantum Monte Carlo simulations
- Convergence of the random batch method for interacting particles with disparate species and weights
- Asymptotic-preserving schemes for multiscale physical problems
- Stein variational gradient descent with learned direction
- Hybrid random batch idea and nonlinear conjugate gradient method for accelerating charged polymer dynamics simulation
- Stein variational gradient descent: many-particle and long-time asymptotics
- A splitting Hamiltonian Monte Carlo method for efficient sampling
- Bayesian model updating with variational inference and Gaussian copula model
- Mean field error estimate of the random batch method for vortex blob dynamics for the 2D Navier--Stokes Equation
This page was built for publication: A stochastic version of Stein variational gradient descent for efficient sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q782348)
