Related papers: Regularized Stein Variational Gradient Flow

Regularized Stein Variational Gradient Flow

URL: http://arxiv.org/abs/2211.07861v2
Date: Thu, 9 May 2024 03:44:47 GMT
Title: Regularized Stein Variational Gradient Flow
Authors: Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur, Jianfeng Lu,
Abstract summary: The Stein Variational Gradient Descent (SVGD) algorithm is a deterministic particle method for sampling. We propose the Regularized Stein Variational Gradient Flow, which interpolates between the Stein Variational Gradient Flow and the Wasserstein Gradient Flow.
Score: 22.69908798297709
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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 the SVGD algorithm (i.e., the Stein Variational Gradient Flow) only provides a constant-order approximation to the Wasserstein Gradient Flow corresponding to the KL-divergence minimization. In this work, we propose the Regularized Stein Variational Gradient Flow, which interpolates between the Stein Variational Gradient Flow and the Wasserstein Gradient Flow. We establish various theoretical properties of the Regularized Stein Variational Gradient Flow (and its time-discretization) including convergence to equilibrium, existence and uniqueness of weak solutions, and stability of the solutions. We provide preliminary numerical evidence of the improved performance offered by the regularization.

Related papers

Bridging the Gap Between Variational Inference and Wasserstein Gradient Flows [6.452626686361619]
We bridge the gap between variational inference and Wasserstein gradient flows. Under certain conditions, the Bures-Wasserstein gradient flow can be recast as the Euclidean gradient flow. We also offer an alternative perspective on the path-derivative gradient, framing it as a distillation procedure to the Wasserstein gradient flow.
arXiv Detail & Related papers (2023-10-31T00:10:19Z)
Particle-based Variational Inference with Generalized Wasserstein Gradient Flow [32.37056212527921]
We propose a ParVI framework, called generalized Wasserstein gradient descent (GWG) We show that GWG exhibits strong convergence guarantees. We also provide an adaptive version that automatically chooses Wasserstein metric to accelerate convergence.
arXiv Detail & Related papers (2023-10-25T10:05:42Z)
Sampling via Gradient Flows in the Space of Probability Measures [10.892894776497165]
Recent work shows that algorithms derived by considering gradient flows in the space of probability measures open up new avenues for algorithm development. This paper makes three contributions to this sampling approach by scrutinizing the design components of such gradient flows.
arXiv Detail & Related papers (2023-10-05T15:20:35Z)
A Finite-Particle Convergence Rate for Stein Variational Gradient Descent [47.6818454221125]
We provide the first finite-particle convergence rate for Stein variational descent gradient (SVGD) Our explicit, non-asymptotic proof strategy will serve as a template for future refinements.
arXiv Detail & Related papers (2022-11-17T17:50:39Z)
Variational Wasserstein gradient flow [9.901677207027806]
We propose a scalable proximal gradient type algorithm for Wasserstein gradient flow. Our framework covers all the classical Wasserstein gradient flows including the heat equation and the porous medium equation.
arXiv Detail & Related papers (2021-12-04T20:27:31Z)
Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
arXiv Detail & Related papers (2021-07-21T17:10:14Z)
Large-Scale Wasserstein Gradient Flows [84.73670288608025]
We introduce a scalable scheme to approximate Wasserstein gradient flows. Our approach relies on input neural networks (ICNNs) to discretize the JKO steps. As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
arXiv Detail & Related papers (2021-06-01T19:21:48Z)
Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization [106.70006655990176]
A distributional optimization problem arises widely in machine learning and statistics. We propose a novel particle-based algorithm, dubbed as variational transport, which approximately performs Wasserstein gradient descent. We prove that when the objective function satisfies a functional version of the Polyak-Lojasiewicz (PL) (Polyak, 1963) and smoothness conditions, variational transport converges linearly.
arXiv Detail & Related papers (2020-12-21T18:33:13Z)
A Non-Asymptotic Analysis for Stein Variational Gradient Descent [44.30569261307296]
We provide a novel finite time analysis for the Stein Variational Gradient Descent algorithm. We provide a descent lemma establishing that the algorithm decreases the objective at each iteration. We also provide a convergence result of the finite particle system corresponding to the practical implementation of SVGD to its population version.
arXiv Detail & Related papers (2020-06-17T12:01:33Z)
A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
arXiv Detail & Related papers (2019-10-31T02:26:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.