Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein space
MZ Diao, K Balasubramanian… - … on Machine Learning, 2023 - proceedings.mlr.press
Variational inference (VI) seeks to approximate a target distribution $\pi $ by an element of a
tractable family of distributions. Of key interest in statistics and machine learning is Gaussian …
tractable family of distributions. Of key interest in statistics and machine learning is Gaussian …
[PDF][PDF] Statistical optimal transport
Statistical Optimal Transport arXiv:2407.18163v2 [math.ST] 7 Nov 2024 Page 1 Statistical
Optimal Transport Sinho Chewi Yale Jonathan Niles-Weed NYU Philippe Rigollet MIT …
Optimal Transport Sinho Chewi Yale Jonathan Niles-Weed NYU Philippe Rigollet MIT …
A finite-particle convergence rate for stein variational gradient descent
We provide the first finite-particle convergence rate for Stein variational gradient descent
(SVGD), a popular algorithm for approximating a probability distribution with a collection of …
(SVGD), a popular algorithm for approximating a probability distribution with a collection of …
Convergence of Stein variational gradient descent under a weaker smoothness condition
L Sun, A Karagulyan… - … Conference on Artificial …, 2023 - proceedings.mlr.press
Abstract Stein Variational Gradient Descent (SVGD) is an important alternative to the
Langevin-type algorithms for sampling from probability distributions of the form $\pi …
Langevin-type algorithms for sampling from probability distributions of the form $\pi …
Provably fast finite particle variants of svgd via virtual particle stochastic approximation
Abstract Stein Variational Gradient Descent (SVGD) is a popular particle-based variational
inference algorithm with impressive empirical performance across various domains …
inference algorithm with impressive empirical performance across various domains …
Towards understanding the dynamics of gaussian-stein variational gradient descent
T Liu, P Ghosal… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Stein Variational Gradient Descent (SVGD) is a nonparametric particle-based
deterministic sampling algorithm. Despite its wide usage, understanding the theoretical …
deterministic sampling algorithm. Despite its wide usage, understanding the theoretical …
Regularized Stein variational gradient flow
The stein variational gradient descent (SVGD) algorithm is a deterministic particle method
for sampling. However, a mean-field analysis reveals that the gradient flow corresponding to …
for sampling. However, a mean-field analysis reveals that the gradient flow corresponding to …
Coin sampling: Gradient-based Bayesian inference without learning rates
L Sharrock, C Nemeth - arXiv preprint arXiv:2301.11294, 2023 - arxiv.org
In recent years, particle-based variational inference (ParVI) methods such as Stein
variational gradient descent (SVGD) have grown in popularity as scalable methods for …
variational gradient descent (SVGD) have grown in popularity as scalable methods for …
Learning rate free sampling in constrained domains
L Sharrock, L Mackey… - Advances in Neural …, 2023 - proceedings.neurips.cc
We introduce a suite of new particle-based algorithms for sampling in constrained domains
which are entirely learning rate free. Our approach leverages coin betting ideas from convex …
which are entirely learning rate free. Our approach leverages coin betting ideas from convex …
Zeroth-order sampling methods for non-log-concave distributions: Alleviating metastability by denoising diffusion
This paper considers the problem of sampling from non-logconcave distribution, based on
queries of its unnormalized density. It first describes a framework, Diffusion Monte Carlo …
queries of its unnormalized density. It first describes a framework, Diffusion Monte Carlo …