English
Related papers

Related papers: Variational Dropout and the Local Reparameterizati…

200 papers

It is well-known that the reparameterisation gradient estimator, which exhibits low variance in practice, is biased for non-differentiable models. This may compromise correctness of gradient-based optimisation methods such as stochastic…

Machine Learning · Computer Science 2024-02-21 Dominik Wagner , Basim Khajwal , C. -H. Luke Ong

Stochastic-gradient MCMC methods enable scalable Bayesian posterior sampling but often suffer from sensitivity to minibatch size and gradient noise. To address this, we propose Stochastic Gradient Lattice Random Walk (SGLRW), an extension…

Stochastic variance reduced gradient (SVRG) is a popular variance reduction technique for accelerating stochastic gradient descent (SGD). We provide a first analysis of the method for solving a class of linear inverse problems in the lens…

Numerical Analysis · Mathematics 2022-01-19 Bangti Jin , Zehui Zhou , Jun Zou

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

Gaussian Process Latent Variable Models (GPLVMs) have become increasingly popular for unsupervised tasks such as dimensionality reduction and missing data recovery due to their flexibility and non-linear nature. An importance-weighted…

Machine Learning · Computer Science 2026-03-10 Jian Xu , Shian Du , Junmei Yang , Qianli Ma , Delu Zeng , John Paisley

Flexible variational distributions improve variational inference but are harder to optimize. In this work we present a control variate that is applicable for any reparameterizable distribution with known mean and covariance matrix, e.g.…

Machine Learning · Computer Science 2020-10-26 Tomas Geffner , Justin Domke

In this paper, a methodology is investigated for signal recovery in the presence of non-Gaussian noise. In contrast with regularized minimization approaches often adopted in the literature, in our algorithm the regularization parameter is…

Optimization and Control · Mathematics 2017-01-23 Yosra Marnissi , Yuling Zheng , Emilie Chouzenoux , Jean-Christophe Pesquet

Sampling methods (e.g., node-wise, layer-wise, or subgraph) has become an indispensable strategy to speed up training large-scale Graph Neural Networks (GNNs). However, existing sampling methods are mostly based on the graph structural…

Machine Learning · Computer Science 2021-09-07 Weilin Cong , Rana Forsati , Mahmut Kandemir , Mehrdad Mahdavi

This work characterizes the benefits of averaging schemes widely used in conjunction with stochastic gradient descent (SGD). In particular, this work provides a sharp analysis of: (1) mini-batching, a method of averaging many samples of a…

Machine Learning · Statistics 2018-08-01 Prateek Jain , Sham M. Kakade , Rahul Kidambi , Praneeth Netrapalli , Aaron Sidford

Surrogate models provide a quick-to-evaluate approximation to complex computational models and are essential for multi-query problems like design optimisation. The inputs of current deterministic computational models are usually…

Applications · Statistics 2024-10-15 Thomas A. Archbold , Ieva Kazlauskaite , Fehmi Cirak

Stochastic-gradient sampling methods are often used to perform Bayesian inference on neural networks. It has been observed that the methods in which notions of differential geometry are included tend to have better performances, with the…

Machine Learning · Computer Science 2024-04-02 Hanlin Yu , Marcelo Hartmann , Bernardo Williams , Arto Klami

This paper theoretically reanalyzes the convergence of the mini-batch stochastic gradient descent (SGD) for a structured minimization problem involving a finite-sum function with its gradient being stochastically approximated, and an…

Optimization and Control · Mathematics 2026-04-07 Runze Li , Jintao Xu , Wenxun Xing

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 by minimizing an…

Machine Learning · Statistics 2023-07-18 Chirag Modi , Charles Margossian , Yuling Yao , Robert Gower , David Blei , Lawrence Saul

Bayesian inference allows us to define a posterior distribution over the weights of a generic neural network (NN). Exact posteriors are usually intractable, in which case approximations can be employed. One such approximation - variational…

Machine Learning · Computer Science 2026-01-30 Andrew Millard , Joshua Murphy , Peter Green , Simon Maskell

Even though dropout is a popular regularization technique, its theoretical properties are not fully understood. In this paper we study dropout regularization in extended generalized linear models based on double exponential families, for…

Machine Learning · Statistics 2024-07-30 Benedikt Lütke Schwienhorst , Lucas Kock , Nadja Klein , David J. Nott

Recent 3D Gaussian Splatting (3DGS) Dropout methods address overfitting under sparse-view conditions by randomly nullifying Gaussian opacities. However, we identify a neighbor compensation effect in these approaches: dropped Gaussians are…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Shuangkang Fang , I-Chao Shen , Xuanyang Zhang , Zesheng Wang , Yufeng Wang , Wenrui Ding , Gang Yu , Takeo Igarashi

Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies…

Machine Learning · Statistics 2024-05-28 Sharmila Karumuri , Ilias Bilionis

In recent years, the shortcomings of Bayesian posteriors as inferential devices have received increased attention. A popular strategy for fixing them has been to instead target a Gibbs measure based on losses that connect a parameter of…

Statistics Theory · Mathematics 2025-04-24 David T. Frazier , Jeremias Knoblauch , Jack Jewson , Christopher Drovandi

In the realm of statistical learning, the increasing volume of accessible data and increasing model complexity necessitate robust methodologies. This paper explores two branches of robust Bayesian methods in response to this trend. The…

Methodology · Statistics 2024-12-02 Masahiro Tanaka

In the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus…

Machine Learning · Statistics 2021-06-14 Kangqiao Liu , Liu Ziyin , Masahito Ueda
‹ Prev 1 3 4 5 6 7 10 Next ›