English
Related papers

Related papers: Bayesian Interpolation with Deep Linear Networks

200 papers

The connection between Bayesian neural networks and Gaussian processes gained a lot of attention in the last few years, with the flagship result that hidden units converge to a Gaussian process limit when the layers width tends to infinity.…

Machine Learning · Statistics 2021-11-30 Mariia Vladimirova , Julyan Arbel , Stéphane Girard

The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet…

Machine Learning · Computer Science 2020-01-17 Wei Hu , Lechao Xiao , Jeffrey Pennington

Bayesian learning has been recently considered as an effective means of accounting for uncertainty in trained deep network parameters. This is of crucial importance when dealing with small or sparse training datasets. On the other hand,…

Machine Learning · Computer Science 2018-02-13 Harris Partaourides , Sotirios Chatzis

Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior. However,…

Machine Learning · Computer Science 2023-07-13 Jihao Andreas Lin , Joe Watson , Pascal Klink , Jan Peters

Laplace approximations are popular techniques for endowing deep networks with epistemic uncertainty estimates as they can be applied without altering the predictions of the trained network, and they scale to large models and datasets. While…

Machine Learning · Computer Science 2024-11-01 Tristan Cinquin , Marvin Pförtner , Vincent Fortuin , Philipp Hennig , Robert Bamler

Quantifying the uncertainty in the output of a neural network is essential for deployment in scientific or engineering applications where decisions must be made under limited or noisy data. Bayesian neural networks (BNNs) provide a…

Machine Learning · Statistics 2026-03-10 Alex Alberts , Ilias Bilionis

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Bayesian inference and kernel methods are well established in machine learning. The neural network Gaussian process in particular provides a concept to investigate neural networks in the limit of infinitely wide hidden layers by using…

Disordered Systems and Neural Networks · Physics 2023-11-10 Javed Lindner , David Dahmen , Michael Krämer , Moritz Helias

Bayesian neural networks utilize probabilistic layers that capture uncertainty over weights and activations, and are trained using Bayesian inference. Since these probabilistic layers are designed to be drop-in replacement of their…

Machine Learning · Computer Science 2021-06-28 Daniel T. Chang

Neural networks have achieved remarkable performance across various problem domains, but their widespread applicability is hindered by inherent limitations such as overconfidence in predictions, lack of interpretability, and vulnerability…

Machine Learning · Statistics 2023-09-29 Julyan Arbel , Konstantinos Pitas , Mariia Vladimirova , Vincent Fortuin

The remarkable performance of overparameterized deep neural networks (DNNs) must arise from an interplay between network architecture, training algorithms, and structure in the data. To disentangle these three components, we apply a…

Machine Learning · Computer Science 2025-07-09 Chris Mingard , Henry Rees , Guillermo Valle-Pérez , Ard A. Louis

Due to the growing adoption of deep neural networks in many fields of science and engineering, modeling and estimating their uncertainties has become of primary importance. Despite the growing literature about uncertainty quantification in…

Machine Learning · Computer Science 2023-02-15 Brian Staber , Sébastien Da Veiga

We perform accurate numerical experiments with fully-connected (FC) one-hidden layer neural networks trained with a discretized Langevin dynamics on the MNIST and CIFAR10 datasets. Our goal is to empirically determine the regimes of…

Disordered Systems and Neural Networks · Physics 2024-01-23 P. Baglioni , R. Pacelli , R. Aiudi , F. Di Renzo , A. Vezzani , R. Burioni , P. Rotondo

What is the best way to exploit extra data -- be it unlabeled data from the same task, or labeled data from a related task -- to learn a given task? This paper formalizes the question using the theory of reference priors. Reference priors…

Machine Learning · Statistics 2022-06-17 Yansong Gao , Rahul Ramesh , Pratik Chaudhari

Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity…

Machine Learning · Computer Science 2022-02-16 Andrew Corbett , Dmitry Kangin

Despite the widespread practical success of deep learning methods, our theoretical understanding of the dynamics of learning in deep neural networks remains quite sparse. We attempt to bridge the gap between the theory and practice of deep…

Neural and Evolutionary Computing · Computer Science 2014-02-20 Andrew M. Saxe , James L. McClelland , Surya Ganguli

Bayesian neural networks (BNNs) offer a natural probabilistic formulation for inference in deep learning models. Despite their popularity, their optimality has received limited attention through the lens of statistical decision theory. In…

Statistics Theory · Mathematics 2026-04-07 Daniel Andrew Coulson , Martin T. Wells

Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafted image priors such as sparsity and low-rank. Unlike learned…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Gauri Jagatap , Chinmay Hegde

Model Compression has drawn much attention within the deep learning community recently. Compressing a dense neural network offers many advantages including lower computation cost, deployability to devices of limited storage and memories,…

Machine Learning · Computer Science 2024-11-04 Diptarka Saha , Zihe Liu , Feng Liang

The aim of this work is to enable inference of deep networks that retain high accuracy for the least possible model complexity, with the latter deduced from the data during inference. To this end, we revisit deep networks that comprise…

Machine Learning · Computer Science 2019-05-07 Konstantinos P. Panousis , Sotirios Chatzis , Sergios Theodoridis
‹ Prev 1 4 5 6 7 8 10 Next ›