中文
相关论文

相关论文: Provably Fast Finite Particle Variants of SVGD via…

200 篇论文

We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution $\pi\propto e^{-V}$ on $\mathbb{R}^d$. In the population limit, SVGD performs gradient…

机器学习 · 统计学 2021-01-05 Anna Korba , Adil Salim , Michael Arbel , Giulia Luise , Arthur Gretton

Stein Variational Gradient Descent (SVGD) is an algorithm for sampling from a target density which is known up to a multiplicative constant. Although SVGD is a popular algorithm in practice, its theoretical study is limited to a few recent…

机器学习 · 计算机科学 2022-06-20 Adil Salim , Lukang Sun , Peter Richtárik

Stein Variational Gradient Descent (SVGD) is a nonparametric particle-based deterministic sampling algorithm. Despite its wide usage, understanding the theoretical properties of SVGD has remained a challenging problem. For sampling from a…

统计理论 · 数学 2023-10-31 Tianle Liu , Promit Ghosal , Krishnakumar Balasubramanian , Natesh S. Pillai

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 particles. Specifically, whenever the target…

机器学习 · 计算机科学 2023-11-03 Jiaxin Shi , Lester Mackey

In this paper we propose and analyze a novel multilevel version of Stein variational gradient descent (SVGD). SVGD is a recent particle based variational inference method. For Bayesian inverse problems with computationally expensive…

数值分析 · 数学 2024-02-05 Simon Weissmann , Jakob Zech

Stein variational gradient descent (SVGD) is a non-parametric inference algorithm that evolves a set of particles to fit a given distribution of interest. We analyze the non-asymptotic properties of SVGD, showing that there exists a set of…

机器学习 · 统计学 2018-10-30 Qiang Liu , Dilin Wang

Particle-based approximate Bayesian inference approaches such as Stein Variational Gradient Descent (SVGD) combine the flexibility and convergence guarantees of sampling methods with the computational benefits of variational inference. In…

机器学习 · 计算机科学 2021-07-30 Lauro Langosco di Langosco , Vincent Fortuin , Heiko Strathmann

Inspired by dynamic programming, we propose Stochastic Virtual Gradient Descent (SVGD) algorithm where the Virtual Gradient is defined by computational graph and automatic differentiation. The method is computationally efficient and has…

机器学习 · 计算机科学 2019-08-01 Zheng Li , Shi Shu

Stein variational gradient descent (SVGD) is a kernel-based particle method for sampling from a target distribution, e.g., in generative modeling and Bayesian inference. SVGD does not require estimating the gradient of the log-density,…

机器学习 · 统计学 2025-04-10 Viktor Stein , Wuchen Li

Stein variational gradient descent (SVGD) is a kernel-based and non-parametric particle method for sampling from a target distribution, such as in Bayesian inference and other machine learning tasks. Different from other particle methods,…

最优化与控制 · 数学 2025-10-02 Viktor Stein , Wuchen Li

Stein Variational Gradient Descent (SVGD) is a widely used sampling algorithm that has been successfully applied in several areas of Machine Learning. SVGD operates by iteratively moving a set of interacting particles (which represent the…

机器学习 · 计算机科学 2024-06-24 Victor Priser , Pascal Bianchi , Adil Salim

Stein variational gradient descent (SVGD) is a general-purpose optimization-based sampling algorithm that has recently exploded in popularity, but is limited by two issues: it is known to produce biased samples, and it can be slow to…

机器学习 · 统计学 2022-04-20 Alex Leviyev , Joshua Chen , Yifei Wang , Omar Ghattas , Aaron Zimmerman

Stein variational gradient descent (SVGD) is a particle-based inference algorithm that leverages gradient information for efficient approximate inference. In this work, we enhance SVGD by leveraging preconditioning matrices, such as the…

机器学习 · 统计学 2019-11-06 Dilin Wang , Ziyang Tang , Chandrajit Bajaj , Qiang Liu

Stein variational gradient descent (SVGD) is a deterministic sampling algorithm that iteratively transports a set of particles to approximate given distributions, based on an efficient gradient-based update that guarantees to optimally…

机器学习 · 统计学 2017-11-15 Qiang Liu

Stein Variational Gradient Descent (SVGD) is an important alternative to the Langevin-type algorithms for sampling from probability distributions of the form $\pi(x) \propto \exp(-V(x))$. In the existing theory of Langevin-type algorithms…

统计理论 · 数学 2022-06-02 Lukang Sun , Avetik Karagulyan , Peter Richtarik

Stein variational gradient descent (SVGD) is a prominent particle-based variational inference method used for sampling a target distribution. SVGD has attracted interest for application in machine-learning techniques such as Bayesian…

机器学习 · 计算机科学 2024-02-26 Yuya Kawamura , Satoshi Takabe

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…

机器学习 · 统计学 2020-06-24 Lei Li , Yingzhou Li , Jian-Guo Liu , Zibu Liu , Jianfeng Lu

Bayesian computation plays an important role in modern machine learning and statistics to reason about uncertainty. A key computational challenge in Bayesian inference is to develop efficient techniques to approximate, or draw samples from…

数值分析 · 数学 2021-09-01 Liang Yan , Tao Zhou

We propose a novel particle-based variational inference method designed to work with multimodal distributions. Our approach, referred to as Branched Stein Variational Gradient Descent (BSVGD), extends the classical Stein Variational…

机器学习 · 计算机科学 2025-07-18 Isaías Bañales , Arturo Jaramillo , Joshué Helí Ricalde-Guerrero

Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional…

机器学习 · 统计学 2018-06-11 Jingwei Zhuo , Chang Liu , Jiaxin Shi , Jun Zhu , Ning Chen , Bo Zhang
‹ 上一页 1 2 3 10 下一页 ›