English
Related papers

Related papers: Batch and match: black-box variational inference w…

200 papers

We study the variational inference problem of minimizing a regularized R\'enyi divergence over an exponential family. We propose to solve this problem with a Bregman proximal gradient algorithm. We propose a sampling-based algorithm to…

Statistics Theory · Mathematics 2024-10-17 Thomas Guilmeau , Emilie Chouzenoux , Víctor Elvira

Stochastic natural gradient variational inference (NGVI) is a popular and efficient algorithm for Bayesian inference. Despite empirical success, the convergence of this method is still not fully understood. In this work, we define and study…

Methodology · Statistics 2026-04-02 Thomas Guilmeau , Hadrien Hendrikx , Florence Forbes

We study batch normalisation in the context of variational inference methods in Bayesian neural networks, such as mean-field or MC Dropout. We show that batch-normalisation does not affect the optimum of the evidence lower bound (ELBO).…

Machine Learning · Computer Science 2020-12-25 Jishnu Mukhoti , Puneet K. Dokania , Philip H. S. Torr , Yarin Gal

For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorithms are a popular approach. For example, Wasserstein VI (WVI) and black-box VI (BBVI) perform…

Machine Learning · Statistics 2026-05-20 Kyurae Kim , Qiang Fu , Yi-An Ma , Jacob R. Gardner , Trevor Campbell

One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation…

Computation · Statistics 2018-05-11 David M. Blei , Alp Kucukelbir , Jon D. McAuliffe

Variational inference is becoming more and more popular for approximating intractable posterior distributions in Bayesian statistics and machine learning. Meanwhile, a few recent works have provided theoretical justification and new…

Statistics Theory · Mathematics 2019-09-09 Badr-Eddine Chérief-Abdellatif

Black-box optimization problems often require simultaneously optimizing different types of variables, such as continuous, integer, and categorical variables. Unlike integer variables, categorical variables do not necessarily have a…

Neural and Evolutionary Computing · Computer Science 2025-05-22 Ryoki Hamano , Shota Saito , Masahiro Nomura , Kento Uchida , Shinichi Shirakawa

Variational inference (VI) is widely used for approximate inference in Bayesian machine learning. In addition to this practical success, generalization bounds for variational inference and related algorithms have been developed, mostly…

Machine Learning · Computer Science 2025-02-19 Yadi Wei , Roni Khardon

We present a Gaussian Variational Inference (GVI) technique that can be applied to large-scale nonlinear batch state estimation problems. The main contribution is to show how to fit both the mean and (inverse) covariance of a Gaussian to…

Robotics · Computer Science 2020-04-13 Timothy D. Barfoot , James R. Forbes , David Yoon

Current variational inference methods for hierarchical Bayesian nonparametric models can neither characterize the correlation structure among latent variables due to the mean-field setting, nor infer the true posterior dimension because of…

Machine Learning · Statistics 2022-04-07 Yirui Liu , Xinghao Qiao , Jessica Lam

In stochastic variational inference, the variational Bayes objective function is optimized using stochastic gradient approximation, where gradients computed on small random subsets of data are used to approximate the true gradient over the…

Methodology · Statistics 2015-10-19 Linda S. L. Tan , David J. Nott

Boosting variational inference (BVI) approximates an intractable probability density by iteratively building up a mixture of simple component distributions one at a time, using techniques from sparse convex optimization to provide both…

Machine Learning · Statistics 2019-10-29 Trevor Campbell , Xinglong Li

Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…

Machine Learning · Computer Science 2025-02-03 Ouya Wang , Shenglong Zhou , Geoffrey Ye Li

We propose denoising diffusion variational inference (DDVI), a black-box variational inference algorithm for latent variable models which relies on diffusion models as flexible approximate posteriors. Specifically, our method introduces an…

Machine Learning · Computer Science 2026-03-16 Wasu Top Piriyakulkij , Yingheng Wang , Volodymyr Kuleshov

The main computational challenge in Bayesian inference is to compute integrals against a high-dimensional posterior distribution. In the past decades, variational inference (VI) has emerged as a tractable approximation to these integrals,…

Statistics Theory · Mathematics 2024-01-09 Anya Katsevich , Philippe Rigollet

Variational families with full-rank covariance approximations are known not to work well in black-box variational inference (BBVI), both empirically and theoretically. In fact, recent computational complexity results for BBVI have…

Machine Learning · Statistics 2025-11-14 Joohwan Ko , Kyurae Kim , Woo Chang Kim , Jacob R. Gardner

Simulation-based inference (SBI) enables Bayesian analysis when the likelihood is intractable but model simulations are available. Recent advances in statistics and machine learning, including Approximate Bayesian Computation and deep…

Methodology · Statistics 2025-09-15 Haoyu Jiang , Yuexi Wang , Yun Yang

Black box variational inference allows researchers to easily prototype and evaluate an array of models. Recent advances allow such algorithms to scale to high dimensions. However, a central question remains: How to specify an expressive…

Machine Learning · Statistics 2016-06-01 Rajesh Ranganath , Dustin Tran , David M. Blei

Modern neural network architectures have achieved remarkable accuracies but remain highly dependent on their training data, often lacking interpretability in their learned mappings. While effective on large datasets, they tend to overfit on…

Machine Learning · Computer Science 2025-03-19 Pavia Bera , Sanjukta Bhanja

We deal with the efficient parallelization of Bayesian global optimization algorithms, and more specifically of those based on the expected improvement criterion and its variants. A closed form formula relying on multivariate Gaussian…

Machine Learning · Statistics 2016-09-12 Sébastien Marmin , Clément Chevalier , David Ginsbourger