English
Related papers

Related papers: Structured Dropout Variational Inference for Bayes…

200 papers

Bayesian neural network posterior distributions have a great number of modes that correspond to the same network function. The abundance of such modes can make it difficult for approximate inference methods to do their job. Recent work has…

Machine Learning · Statistics 2024-07-03 Tommy Rochussen

This paper proposes to generalize the variational recurrent neural network (RNN) with variational inference (VI)-based dropout regularization employed for the long short-term memory (LSTM) cells to more advanced RNN architectures like gated…

Computation and Language · Computer Science 2020-09-03 Jun Qi , Xu Liu , Javier Tejedor

Dropout has recently emerged as a powerful and simple method for training neural networks preventing co-adaptation by stochastically omitting neurons. Dropout is currently not grounded in explicit modelling assumptions which so far has…

Machine Learning · Statistics 2022-05-18 Tue Herlau , Morten Mørup , Mikkel N. Schmidt

Bayesian methods have proved powerful in many applications for the inference of model parameters from data. These methods are based on Bayes' theorem, which itself is deceptively simple. However, in practice the computations required are…

Methodology · Statistics 2020-07-10 Michael A. Chappell , Mark W. Woolrich

Bayesian methods estimate a measure of uncertainty by using the posterior distribution. One source of difficulty in these methods is the computation of the normalizing constant. Calculating exact posterior is generally intractable and we…

Machine Learning · Computer Science 2021-11-17 Farzaneh Mahdisoltani

Solving high-dimensional PDE-governed inverse problems is often challenging due to complex non-Gaussian posterior distributions, expensive forward model evaluations, and misspecified prior information. To address these issues, we propose a…

Machine Learning · Computer Science 2026-05-29 Yueyang Wang , Xili Wang , Kejun Tang , Xiaoliang Wan , Tao Zhou , Chao Yang

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

We introduce a variational Bayesian neural network where the parameters are governed via a probability distribution on random matrices. Specifically, we employ a matrix variate Gaussian \cite{gupta1999matrix} parameter posterior…

Machine Learning · Statistics 2016-06-24 Christos Louizos , Max Welling

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

Deep learning has been the engine powering many successes of data science. However, the deep neural network (DNN), as the basic model of deep learning, is often excessively over-parameterized, causing many difficulties in training,…

Machine Learning · Statistics 2021-03-09 Yan Sun , Qifan Song , Faming Liang

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded…

Machine Learning · Statistics 2016-10-05 Yarin Gal , Zoubin Ghahramani

We propose VISP: Volatility Informed Stochastic Projection, an adaptive regularization method that leverages gradient volatility to guide stochastic noise injection in deep neural networks. Unlike conventional techniques that apply uniform…

Machine Learning · Computer Science 2025-09-03 Tanvir Islam

Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and generalization, and data inefficiency. However, scaling Bayesian inference to large architectures is…

Structured variational inference constitutes a core methodology in modern statistical applications. Unlike mean-field variational inference, the approximate posterior is assumed to have interdependent structure. We consider the natural…

Machine Learning · Statistics 2025-11-14 Shunan Sheng , Bohan Wu , Bennett Zhu , Sinho Chewi , Aram-Alexandre Pooladian

Blind image denoising is an important yet very challenging problem in computer vision due to the complicated acquisition process of real images. In this work we propose a new variational inference method, which integrates both noise…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Zongsheng Yue , Hongwei Yong , Qian Zhao , Lei Zhang , Deyu Meng

Bayesian posterior inference is prevalent in various machine learning problems. Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accuracy of resulting…

Machine Learning · Computer Science 2018-07-11 Guoqing Zheng , Yiming Yang , Jaime Carbonell

We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models for cross-domain knowledge transfer, to address acoustic mismatches between training and testing conditions.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-22 Hu Hu , Sabato Marco Siniscalchi , Chao-Han Huck Yang , Chin-Hui Lee

Bayesian inference provides principled uncertainty quantification, but accurate posterior sampling with MCMC can be computationally prohibitive for modern applications. Variational inference (VI) offers a scalable alternative and often…

Methodology · Statistics 2026-05-14 Laura Battaglia , Stefano Cortinovis , Chris Holmes , David T. Frazier , Jack Jewson

Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap Bayesian inference.…

Machine Learning · Statistics 2019-05-30 Eric Nalisnick , José Miguel Hernández-Lobato , Padhraic Smyth

Continuous-time Bayesian networks (CTBNs) constitute a general and powerful framework for modeling continuous-time stochastic processes on networks. This makes them particularly attractive for learning the directed structures among…

Machine Learning · Statistics 2018-10-15 Dominik Linzner , Heinz Koeppl