English
Related papers

Related papers: Alpha-Divergences in Variational Dropout

200 papers

We propose a robust and scalable variational Bayes (VB) framework designed to effectively handle contamination and outliers in dataset. Our approach partitions the data into $m$ disjoint subsets and formulates a joint optimization problem…

Methodology · Statistics 2025-12-16 Jiawei Yan , Ju Liu , Weidong Liu , Jiyuan Tu

Modern variational inference (VI) uses stochastic gradients to avoid intractable expectations, enabling large-scale probabilistic inference in complex models. VI posits a family of approximating distributions q and then finds the member of…

Machine Learning · Statistics 2021-02-24 Christian A. Naesseth , Fredrik Lindsten , David Blei

Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a loss that is typically the (reverse) Kullback-Leibler (KL)…

Machine Learning · Statistics 2025-11-18 Marguerite Petit-Talamon , Marc Lambert , Anna Korba

Variational Bayes (VB) is a popular tool for Bayesian inference in statistical modeling. Recently, some VB algorithms are proposed to handle intractable likelihoods with applications such as approximate Bayesian computation. In this paper,…

Numerical Analysis · Mathematics 2021-09-28 Zhijian He , Zhenghang Xu , Xiaoqun Wang

Variational Inference approximates an unnormalized distribution via the minimization of Kullback-Leibler (KL) divergence. Although this divergence is efficient for computation and has been widely used in applications, it suffers from some…

Machine Learning · Statistics 2022-07-28 Mingxuan Yi , Song Liu

We interpret likelihood-based test functions from a geometric perspective where the Kullback-Leibler (KL) divergence is adopted to quantify the distance from a distribution to another. Such a test function can be seen as a sub-Gaussian…

Information Theory · Computer Science 2021-01-05 Yan Wang

In Bayesian machine learning, the posterior distribution is typically computationally intractable, hence variational inference is often required. In this approach, an evidence lower bound on the log likelihood of data is maximized during…

Machine Learning · Computer Science 2019-07-23 Stephen Odaibo

Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks. The main contribution of the…

Machine Learning · Statistics 2018-07-06 Jiri Hron , Alexander G. de G. Matthews , Zoubin Ghahramani

Robustness to outliers is a central issue in real-world machine learning applications. While replacing a model to a heavy-tailed one (e.g., from Gaussian to Student-t) is a standard approach for robustification, it can only be applied to…

Machine Learning · Statistics 2018-03-01 Futoshi Futami , Issei Sato , Masashi Sugiyama

Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application,…

Machine Learning · Statistics 2018-05-11 Adam D. Cobb , Stephen J. Roberts , Yarin Gal

In statistical classification/multiple hypothesis testing and machine learning, a model distribution estimated from the training data is usually applied to replace the unknown true distribution in the Bayes decision rule, which introduces a…

Information Theory · Computer Science 2024-09-24 Zijian Yang , Vahe Eminyan , Ralf Schlüter , Hermann Ney

We develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To…

Machine Learning · Statistics 2019-05-29 Francisco J. R. Ruiz , Michalis K. Titsias

In this paper, we derive a useful lower bound for the Kullback-Leibler divergence (KL-divergence) based on the Hammersley-Chapman-Robbins bound (HCRB). The HCRB states that the variance of an estimator is bounded from below by the…

Statistics Theory · Mathematics 2019-11-05 Tomohiro Nishiyama

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the…

Machine Learning · Computer Science 2025-07-31 Adwait Datar , Nihat Ay

Coupling arguments are a central tool for bounding the deviation between two stochastic processes, but traditionally have been limited to Wasserstein metrics. In this paper, we apply the shifted composition rule--an information-theoretic…

Statistics Theory · Mathematics 2024-12-25 Jason M. Altschuler , Sinho Chewi

We propose a family of variational approximations to Bayesian posterior distributions, called $\alpha$-VB, with provable statistical guarantees. The standard variational approximation is a special case of $\alpha$-VB with $\alpha=1$. When…

Statistics Theory · Mathematics 2018-02-09 Yun Yang , Debdeep Pati , Anirban Bhattacharya

This short note is on a property of the Kullback-Leibler (KL) divergence which indicates that independent Gaussian distributions minimize the KL divergence from given independent Gaussian distributions. The primary purpose of this note is…

Information Theory · Computer Science 2020-12-04 Song Fang , Quanyan Zhu

While Deep Neural Networks (DNNs) achieve remarkable performance, their tendency to produce overconfident predictions. Evidential Deep Learning (EDL) mitigates this by formulating predictions as a Dirichlet distribution over class…

Machine Learning · Computer Science 2026-05-27 Jiawei Tang , Xinyan Du , Hui Liu , Junhui Hou , Yuheng Jia

Variational Bayes (VB) is a popular scalable alternative to Markov chain Monte Carlo for Bayesian inference. We study a mean-field spike and slab VB approximation of widely used Bayesian model selection priors in sparse high-dimensional…

Machine Learning · Statistics 2021-09-07 Kolyan Ray , Botond Szabo , Gabriel Clara

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over…

Computation and Language · Computer Science 2024-12-10 Taiqiang Wu , Chaofan Tao , Jiahao Wang , Runming Yang , Zhe Zhao , Ngai Wong