paper-with-me

Papers

Batch and match: black-box variational inference with a score-based divergence

2024-02-22 · Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul

Most leading implementations of black-box variational inference (BBVI) are based on optimizing a stochastic evidence lower bound (ELBO). But such approaches to BBVI often converge slowly due to the high variance of their gradient estimates and their sensitivity to hyperparameters. In this work, we propose batch and match (BaM), an alternative approach to BBVI based on a score-based divergence. Notably, this score-based divergence can be optimized by a closed-form proximal update for Gaussian variational families with full covariance matrices. We analyze the convergence of BaM when the target distribution is Gaussian, and we prove that in the limit of infinite batch size the variational parameter updates converge exponentially quickly to the target mean and covariance. We also evaluate the performance of BaM on Gaussian and non-Gaussian target distributions that arise from posterior inference in hierarchical and deep generative models. In these experiments, we find that BaM typically converges in fewer (and sometimes significantly fewer) gradient evaluations than leading implementations of BBVI based on ELBO maximization.

📄 PDF Abstract BibTeX arXiv:2402.14758

Code (2)

modichirag/gsm-vi 공식 구현 jax
roualdes/bridgestan 공식 구현

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음
BAM Park et al. proposed the bottleneck attention module (BAM), aiming to efficiently improve the representational capability of networks. It uses dilated convolution to enlarge…

Similar Papers 제목 키워드 기반

Batch, match, and patch: low-rank approximations for score-based variational inference

2024-10-29 · Chirag Modi, Diana Cai, Lawrence K. Saul

Black-box variational inference (BBVI) scales poorly to high-dimensional problems when it is used to estimate a multivariate Gaussian approximation with a full covariance matrix. In this paper, we extend the batch-and-ma…

Variational Inference

Variational Inference with Gaussian Score Matching

2023-07-15 · NeurIPS 2023 11 · Chirag Modi, Charles Margossian, Yuling Yao, Robert Gower 외

Variational inference (VI) is a method to approximate the computationally intractable posterior distributions that arise in Bayesian statistics. Typically, VI fits a simple parametric distribution to the target posterior…

Bayesian InferenceVariational Inference

Fast Black-box Variational Inference through Stochastic Trust-Region Optimization

2017-06-07 · NeurIPS 2017 12 · Jeffrey Regier, Michael. I. Jordan, Jon Mcauliffe

We introduce TrustVI, a fast second-order algorithm for black-box variational inference based on trust-region optimization and the reparameterization trick. At each iteration, TrustVI proposes and assesses a step based o…

Variational Inference

Large-scale Score-based Variational Posterior Inference for Bayesian Deep Neural Networks

2026-02-05 · Minyoung Kim arxiv

Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertainty quantification, robustness to noise, resistance to overfitting, and m…

Fisher meets Feynman: score-based variational inference with a product of experts

2025-10-24 · Diana Cai, Robert M. Gower, David M. Blei, Lawrence K. Saul arxiv

We introduce a highly expressive yet distinctly tractable family for black-box variational inference (BBVI). Each member of this family is a weighted product of experts (PoE), and each weighted expert in the product is p…