paper-with-me

Papers

Branching Stein Variational Gradient Descent for sampling multimodal distributions

2025-06-16 · Isaias Banales, Arturo Jaramillo, Heli Ricalde Guerrero

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 Gradient Descent (SVGD) algorithm by incorporating a random branching mechanism that encourages the exploration of the state space. In this work, a theoretical guarantee for the convergence in distribution is presented, as well as numerical experiments to validate the suitability of our algorithm. Performance comparisons between the BSVGD and the SVGD are presented using the Wasserstein distance between samples and the corresponding computational times.

📄 PDF Abstract BibTeX arXiv:2506.13916

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Regularized Stein Variational Gradient Flow

2022-11-15 · Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur, Jianfeng Lu

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 …

Stein Variational Gradient Descent as Gradient Flow

2017-04-25 · NeurIPS 2017 12 · 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 guarante…

A stochastic version of Stein Variational Gradient Descent for efficient sampling

2019-02-09 · Lei Li, Yingzhou Li, Jian-Guo Liu, Zibu Liu 외

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 t…

Bayesian Inference

VAE Learning via Stein Variational Gradient Descent

2017-04-18 · NeurIPS 2017 12 · Yunchen Pu, Zhe Gan, Ricardo Henao, Chunyuan Li 외

A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent. A key advantage of this approach is that one need not make parametric assumptions about the form of the…

A Note on the Convergence of Mirrored Stein Variational Gradient Descent under $(L_0,L_1)-$Smoothness Condition

2022-06-20 · Lukang Sun, Peter Richtárik

In this note, we establish a descent lemma for the population limit Mirrored Stein Variational Gradient Method~(MSVGD). This descent lemma does not rely on the path information of MSVGD but rather on a simple assumption …

LEMMA