English
Related papers

Related papers: Optimality of Sub-network Laplace Approximations: …

200 papers

The Bayesian paradigm has the potential to solve core issues of deep neural networks such as poor calibration and data inefficiency. Alas, scaling Bayesian inference to large weight spaces often requires restrictive approximations. In this…

Subspace inference for neural networks assumes that a subspace of their parameter space suffices to produce a reliable uncertainty quantification. In this work, we underpin the validity of this assumption by using low rank techniques. We…

Machine Learning · Computer Science 2026-04-13 Josua Faller , Jörg Martin

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

The Laplace approximation provides a closed-form model selection objective for neural networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters, like weight decay strength, have seen renewed interest in the…

Machine Learning · Computer Science 2024-01-10 Jihao Andreas Lin , Javier Antorán , José Miguel Hernández-Lobato

Selecting hyperparameters in deep learning greatly impacts its effectiveness but requires manual effort and expertise. Recent works show that Bayesian model selection with Laplace approximations can allow to optimize such hyperparameters…

Large neural networks trained on large datasets have become the dominant paradigm in machine learning. These systems rely on maximum likelihood point estimates of their parameters, precluding them from expressing model uncertainty. This may…

Machine Learning · Statistics 2024-05-01 Javier Antoran

Bayesian inference on non-Gaussian data is often non-analytic and requires computationally expensive approximations such as sampling or variational inference. We propose an approximate inference framework primarily designed to be…

Machine Learning · Computer Science 2022-10-12 Marius Hobbhahn , Philipp Hennig

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

Laplace's method, a family of asymptotic methods used to approximate integrals, is presented as a potential candidate for the tool box of techniques used for knowledge acquisition and probabilistic inference in belief networks with…

Artificial Intelligence · Computer Science 2013-02-28 Adriano Azevedo-Filho , Ross D. Shachter

The hierarchical prior used in Latent Gaussian models (LGMs) induces a posterior geometry prone to frustrate inference algorithms. Marginalizing out the latent Gaussian variable using an integrated Laplace approximation removes the…

Computation · Statistics 2023-06-28 Charles C. Margossian

Deep neural networks (DNNs) often produce overconfident out-of-distribution predictions, motivating Bayesian uncertainty quantification. The Linearized Laplace Approximation (LLA) achieves this by linearizing the DNN and applying Laplace…

Machine Learning · Statistics 2026-02-04 Pedro Jiménez , Luis A. Ortega , Pablo Morales-Álvarez , Daniel Hernández-Lobato

Uncertainty quantification for deep neural networks has recently evolved through many techniques. In this work, we revisit Laplace approximation, a classical approach for posterior approximation that is computationally attractive. However,…

Machine Learning · Computer Science 2021-07-14 Christian S. Perone , Roberto Pereira Silveira , Thomas Paula

The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community. The method provides reliable error bars and admits a closed-form expression for the model evidence,…

Popular deterministic approximations of posterior distributions from, e.g. the Laplace method, variational Bayes and expectation-propagation, generally rely on symmetric approximating families, often taken to be Gaussian. This choice…

Methodology · Statistics 2026-01-19 Francesco Pozza , Daniele Durante , Botond Szabo

In Bayesian inference, making deductions about a parameter of interest requires one to sample from or compute an integral against a posterior distribution. A popular method to make these computations cheaper in high-dimensional settings is…

Statistics Theory · Mathematics 2024-06-10 Anya Katsevich

In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian deep learning…

Machine Learning · Statistics 2020-07-24 Alexander Immer

Using a hierarchical construction, we develop methods for a wide and flexible class of models by taking a fully parametric approach to generalized linear mixed models with complex covariance dependence. The Laplace approximation is used to…

Methodology · Statistics 2024-07-31 Jay M. Ver Hoef , Eryn Blagg , Michael Dumelle , Philip M. Dixon , Dale L. Zimmerman , Paul Conn

Given a finite set of sample points, meta-learning algorithms aim to learn an optimal adaptation strategy for new, unseen tasks. Often, this data can be ambiguous as it might belong to different tasks concurrently. This is particularly the…

Machine Learning · Computer Science 2024-10-24 Alfredo Reichlin , Gustaf Tegnér , Miguel Vasco , Hang Yin , Mårten Björkman , Danica Kragic

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

In recent years, various subspace algorithms have been developed to handle large-scale optimization problems. Although existing subspace Newton methods require fewer iterations to converge in practice, the matrix operations and full…

Optimization and Control · Mathematics 2024-06-05 Taisei Miyaishi , Ryota Nozawa , Pierre-Louis Poirion , Akiko Takeda
‹ Prev 1 2 3 10 Next ›