English
Related papers

Related papers: Eigenvalue Corrected Noisy Natural Gradient

200 papers

Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy gradients often used in…

Machine Learning · Statistics 2017-05-23 Andrew C. Miller , Nicholas J. Foti , Alexander D'Amour , Ryan P. Adams

Accelerated MRI reconstruction involves solving an ill-posed inverse problem where noise in acquired data propagates to the reconstructed images. Noise analyses are central to MRI reconstruction for providing an explicit measure of solution…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Onat Dalmaz , Arjun D. Desai , Reinhard Heckel , Tolga Çukur , Akshay S. Chaudhari , Brian A. Hargreaves

We propose a novel adaptive importance sampling scheme for Bayesian inversion problems where the inference of the variables of interest and the power of the data noise is split. More specifically, we consider a Bayesian analysis for the…

Computation · Statistics 2021-07-27 L. Martino , F. Llorente , E. Curbelo , J. Lopez-Santiago , J. Miguez

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

This paper investigates the consistency of a posterior distribution in the single-measurement fractional Calder\'on problem with additive Gaussian noise. We consider a Bayesian framework with rescaled and Gaussian sieve priors, using a…

Statistics Theory · Mathematics 2025-11-17 Pu-Zhao Kow , Janne Nurminen , Jesse Railo

Uncertainty computation in deep learning is essential to design robust and reliable systems. Variational inference (VI) is a promising approach for such computation, but requires more effort to implement and execute compared to…

Machine Learning · Statistics 2018-08-03 Mohammad Emtiyaz Khan , Didrik Nielsen , Voot Tangkaratt , Wu Lin , Yarin Gal , Akash Srivastava

In this article a novel approach for training deep neural networks using Bayesian techniques is presented. The Bayesian methodology allows for an easy evaluation of model uncertainty and additionally is robust to overfitting. These are…

Machine Learning · Computer Science 2019-04-03 Konstantin Posch , Jürgen Pilz

While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neural network and the storage of intermediate activations.…

Machine Learning · Computer Science 2025-11-06 Daniel Wang , Evan Markou , Dylan Campbell

We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient…

Machine Learning · Computer Science 2020-01-01 Wesley Maddox , Timur Garipov , Pavel Izmailov , Dmitry Vetrov , Andrew Gordon Wilson

Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…

Machine Learning · Statistics 2026-01-06 Hai-Vy Nguyen , Fabrice Gamboa , Sixin Zhang , Reda Chhaibi , Serge Gratton , Thierry Giaccone

Heteroscedastic regression models a Gaussian variable's mean and variance as a function of covariates. Parametric methods that employ neural networks for these parameter maps can capture complex relationships in the data. Yet, optimizing…

Machine Learning · Computer Science 2022-12-20 Andrew Stirn , Hans-Hermann Wessels , Megan Schertzer , Laura Pereira , Neville E. Sanjana , David A. Knowles

We investigate unbiased high-dimensional mean estimators in differential privacy. We consider differentially private mechanisms whose expected output equals the mean of the input dataset, for every dataset drawn from a fixed bounded…

Statistics Theory · Mathematics 2023-12-22 Aleksandar Nikolov , Haohua Tang

The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models. However, typical assumptions on the approximate posterior distribution of the encoder and/or the prior, seriously…

Machine Learning · Computer Science 2020-07-13 Ifigeneia Apostolopoulou , Elan Rosenfeld , Artur Dubrawski

Bayesian models often involve a small set of hyperparameters determined by maximizing the marginal likelihood. Bayesian optimization is a popular iterative method where a Gaussian process posterior of the underlying function is sequentially…

Computation · Statistics 2022-08-18 Oskar Gustafsson , Mattias Villani , Pär Stockhammar

Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad…

Machine Learning · Computer Science 2021-05-18 Xingyi Yang

Heteroscedastic regression considering the varying noises among observations has many applications in the fields like machine learning and statistics. Here we focus on the heteroscedastic Gaussian process (HGP) regression which integrates…

Machine Learning · Statistics 2020-01-22 Haitao Liu , Yew-Soon Ong , Jianfei Cai

A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer. Recent work [Riquelme et al., 2018, Azizzadenesheli et al., 2018]…

Machine Learning · Computer Science 2019-12-17 John Moberg , Lennart Svensson , Juliano Pinto , Henk Wymeersch

Grazing incidence X-ray fluorescence is a non-destructive technique for analyzing the geometry and compositional parameters of nanostructures appearing e.g. in computer chips. In this paper, we propose to reconstruct the posterior parameter…

Machine Learning · Computer Science 2021-02-08 Anna Andrle , Nando Farchmin , Paul Hagemann , Sebastian Heidenreich , Victor Soltwisch , Gabriele Steidl

The core components of many modern neural network architectures, such as transformers, convolutional, or graph neural networks, can be expressed as linear layers with $\textit{weight-sharing}$. Kronecker-Factored Approximate Curvature…

Machine Learning · Computer Science 2024-01-12 Runa Eschenhagen , Alexander Immer , Richard E. Turner , Frank Schneider , Philipp Hennig

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