English
Related papers

Related papers: Variational Dropout and the Local Reparameterizati…

200 papers

MC Dropout is a mainstream "free lunch" method in medical imaging for approximate Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC and uncertainty quantification in Neural Networks (NNs); to fall…

We propose DropMax, a stochastic version of softmax classifier which at each iteration drops non-target classes according to dropout probabilities adaptively decided for each instance. Specifically, we overlay binary masking variables over…

Machine Learning · Computer Science 2018-11-05 Hae Beom Lee , Juho Lee , Saehoon Kim , Eunho Yang , Sung Ju Hwang

Variational inference techniques based on inducing variables provide an elegant framework for scalable posterior estimation in Gaussian process (GP) models. Besides enabling scalability, one of their main advantages over sparse…

Machine Learning · Statistics 2021-02-24 Simone Rossi , Markus Heinonen , Edwin V. Bonilla , Zheyang Shen , Maurizio Filippone

We analyze the convergence rate of gradient flows on objective functions induced by Dropout and Dropconnect, when applying them to shallow linear Neural Networks (NNs) - which can also be viewed as doing matrix factorization using a…

Machine Learning · Computer Science 2020-12-04 Albert Senen-Cerda , Jaron Sanders

Bayesian Neural Networks provide a principled framework for uncertainty quantification by modeling the posterior distribution of network parameters. However, exact posterior inference is computationally intractable, and widely used…

Machine Learning · Computer Science 2025-12-02 Alfredo Reichlin , Miguel Vasco , Danica Kragic

We introduce Gradient Agreement Filtering (GAF) to improve on gradient averaging in distributed deep learning optimization. Traditional distributed data-parallel stochastic gradient descent involves averaging gradients of microbatches to…

Machine Learning · Computer Science 2024-12-31 Francois Chaubard , Duncan Eddy , Mykel J. Kochenderfer

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This…

Machine Learning · Computer Science 2024-11-06 Hanrui Yan , Dan Shao

Variational inference has recently emerged as a popular alternative to the classical Markov chain Monte Carlo (MCMC) in large-scale Bayesian inference. The core idea is to trade statistical accuracy for computational efficiency. In this…

Machine Learning · Statistics 2023-08-08 Kush Bhatia , Nikki Lijing Kuang , Yi-An Ma , Yixin Wang

The Gaussian process latent variable model (GP-LVM) provides a flexible approach for non-linear dimensionality reduction that has been widely applied. However, the current approach for training GP-LVMs is based on maximum likelihood, where…

Machine Learning · Statistics 2014-09-09 Andreas C. Damianou , Michalis K. Titsias , Neil D. Lawrence

Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However, the gap between dropout's training and inference phases,…

Machine Learning · Computer Science 2017-02-17 Xuezhe Ma , Yingkai Gao , Zhiting Hu , Yaoliang Yu , Yuntian Deng , Eduard Hovy

Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principled posterior updating…

Machine Learning · Statistics 2021-06-15 Sanyam Kapoor , Theofanis Karaletsos , Thang D. Bui

Stochastic gradient Markov Chain Monte Carlo (SG-MCMC) has been developed as a flexible family of scalable Bayesian sampling algorithms. However, there has been little theoretical analysis of the impact of minibatch size to the algorithm's…

Machine Learning · Statistics 2017-09-06 Changyou Chen , Wenlin Wang , Yizhe Zhang , Qinliang Su , Lawrence Carin

When preparing a Gibbs sampler, some conditionals may be unfamiliar distributions without well-known variate generation routines. Rejection sampling may be used to draw from such distributions exactly; however, it can be challenging to…

Methodology · Statistics 2025-09-23 Andrew M. Raim , Kyle M. Irimata , James A. Livsey

We introduce a novel stochastic variational inference method for Gaussian process ($\mathcal{GP}$) regression, by deriving a posterior over a learnable set of coresets: i.e., over pseudo-input/output, weighted pairs. Unlike former free-form…

Machine Learning · Computer Science 2025-03-06 Mert Ketenci , Adler Perotte , Noémie Elhadad , Iñigo Urteaga

Deriving Bayesian inference for exponential random graph models (ERGMs) is a challenging "doubly intractable" problem as the normalizing constants of the likelihood and posterior density are both intractable. Markov chain Monte Carlo (MCMC)…

Computation · Statistics 2019-11-26 Linda S. L. Tan , Nial Friel

Variational methods are employed in situations where exact Bayesian inference becomes intractable due to the difficulty in performing certain integrals. Typically, variational methods postulate a tractable posterior and formulate a lower…

Machine Learning · Statistics 2019-06-12 Nikolaos Gianniotis , Christoph Schnörr , Christian Molkenthin , Sanjay Singh Bora

This paper presents a new variable selection approach integrated with Gaussian process (GP) regression. We consider a sparse projection of input variables and a general stationary covariance model that depends on the Euclidean distance…

Machine Learning · Computer Science 2020-08-26 Chiwoo Park , David J. Borth , Nicholas S. Wilson , Chad N. Hunter

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an…

Machine Learning · Statistics 2020-02-04 Kenji Kawaguchi , Haihao Lu

Mixtures of linear mixed models (MLMMs) are useful for clustering grouped data and can be estimated by likelihood maximization through the EM algorithm. The conventional approach to determining a suitable number of components is to compare…

Applications · Statistics 2014-05-26 Siew Li Tan , David J. Nott

In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify…

Machine Learning · Computer Science 2019-06-25 Zhilu Zhang , Adrian V. Dalca , Mert R. Sabuncu
‹ Prev 1 8 9 10 Next ›