paper-with-me

홈 › Papers

A Particle Algorithm for Mean-Field Variational Inference

2024-12-29 · Qiang Du, Kaizheng Wang, Edith Zhang, Chenyang Zhong

Variational inference is a fast and scalable alternative to Markov chain Monte Carlo and has been widely applied to posterior inference tasks in statistics and machine learning. A traditional approach for implementing mean-field variational inference (MFVI) is coordinate ascent variational inference (CAVI), which relies crucially on parametric assumptions on complete conditionals. In this paper, we introduce a novel particle-based algorithm for mean-field variational inference, which we term PArticle VI (PAVI). Notably, our algorithm does not rely on parametric assumptions on complete conditionals, and it applies to the nonparametric setting. We provide non-asymptotic finite-particle convergence guarantee for our algorithm. To our knowledge, this is the first end-to-end guarantee for particle-based MFVI.

📄 PDF Abstract BibTeX arXiv:2412.20385

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

DPVI: A Dynamic-Weight Particle-Based Variational Inference Framework

2021-12-02 · Chao Zhang, Zhijian Li, Hui Qian, Xin Du

The recently developed Particle-based Variational Inference (ParVI) methods drive the empirical distribution of a set of \emph{fixed-weight} particles towards a given target distribution $\pi$ by iteratively updating par…

Variational Inference

Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent

2023-05-23 · NeurIPS 2023 11

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. F…

Variational Inference

Particle Mean Field Variational Bayes

2023-03-24 · Minh-Ngoc Tran, Paco Tseng, Robert Kohn

The Mean Field Variational Bayes (MFVB) method is one of the most computationally efficient techniques for Bayesian inference. However, its use has been restricted to models with conjugate priors or those that require an…

Bayesian Inferenceregression

Variational Particle Approximations

2014-02-24 · Ardavan Saeedi, Tejas D. Kulkarni, Vikash Mansinghka, Samuel Gershman

Approximate inference in high-dimensional, discrete probabilistic models is a central problem in computational statistics and machine learning. This paper describes discrete particle variational inference (DPVI), a new a…

Spike SortingVariational Inference

Mean-field Variational Inference via Wasserstein Gradient Flow

2022-07-17 · Rentian Yao, Yun Yang

Variational inference, such as the mean-field (MF) approximation, requires certain conjugacy structures for efficient computation. These can impose unnecessary restrictions on the viable prior distribution family and fur…

Bayesian InferenceVariational Inference