English
Related papers

Related papers: Addressing the Inconsistency in Bayesian Deep Lear…

200 papers

In this paper we study properties of the Laplace approximation of the posterior distribution arising in nonlinear Bayesian inverse problems. Our work is motivated by Schillings et al. (2020), where it is shown that in such a setting the…

Numerical Analysis · Mathematics 2024-04-09 Tapio Helin , Remo Kretschmann

Predictions made by deep learning models are prone to data perturbations, adversarial attacks, and out-of-distribution inputs. To build a trusted AI system, it is therefore critical to accurately quantify the prediction uncertainties. While…

Machine Learning · Computer Science 2023-04-12 Hanjing Wang , Dhiraj Joshi , Shiqiang Wang , Qiang Ji

Constrained learning is prevalent in many statistical tasks. Recent work proposes distance-to-set penalties to derive estimators under general constraints that can be specified as sets, but focuses on obtaining point estimates that do not…

Methodology · Statistics 2022-10-25 Rick Presman , Jason Xu

Benchmark datasets used for image classification tend to have very low levels of label noise. When Bayesian neural networks are trained on these datasets, they often underfit, misrepresenting the aleatoric uncertainty of the data. A common…

Machine Learning · Computer Science 2024-03-05 Martin Marek , Brooks Paige , Pavel Izmailov

Although theoretically compelling, Bayesian learning with modern machine learning models is computationally challenging since it requires approximating a high dimensional posterior distribution. In this work, we (i) introduce posteriors, an…

Machine Learning · Computer Science 2025-04-15 Samuel Duffield , Kaelan Donatella , Johnathan Chiu , Phoebe Klett , Daniel Simpson

As we move away from the data, the predictive uncertainty should increase, since a great variety of explanations are consistent with the little available information. We introduce Distance-Aware Prior (DAP) calibration, a method to correct…

Machine Learning · Statistics 2022-07-19 Gianluca Detommaso , Alberto Gasparin , Andrew Wilson , Cedric Archambeau

Large-scale linear models are ubiquitous throughout machine learning, with contemporary application as surrogate models for neural network uncertainty quantification; that is, the linearised Laplace method. Alas, the computational cost…

Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts,…

Machine Learning · Computer Science 2022-04-04 Martin Mundt , Iuliia Pliushch , Sagnik Majumder , Yongwon Hong , Visvanathan Ramesh

Bayesian models are a powerful tool for studying complex data, allowing the analyst to encode rich hierarchical dependencies and leverage prior information. Most importantly, they facilitate a complete characterization of uncertainty…

Machine Learning · Statistics 2023-04-25 Steven Winter , Trevor Campbell , Lizhen Lin , Sanvesh Srivastava , David B. Dunson

In the literature surrounding Bayesian penalized regression, the two primary choices of prior distribution on the regression coefficients are zero-mean Gaussian and Laplace. While both have been compared numerically and theoretically, there…

Methodology · Statistics 2010-01-26 Luke Bornn , Raphael Gottardo , Arnaud Doucet

Bayesian inference is used extensively to quantify the uncertainty in an inferred field given the measurement of a related field when the two are linked by a mathematical model. Despite its many applications, Bayesian inference faces…

Machine Learning · Statistics 2020-03-31 Dhruv V. Patel , Assad A. Oberai

Although Gaussian processes (GPs) with deep kernels have been successfully used for meta-learning in regression tasks, its uncertainty estimation performance can be poor. We propose a meta-learning method for calibrating deep kernel GPs for…

Machine Learning · Statistics 2023-12-14 Tomoharu Iwata , Atsutoshi Kumagai

Uncertainty quantification in deep learning is crucial for safe and reliable decision-making in downstream tasks. Existing methods quantify uncertainty at the last layer or other approximations of the network which may miss some sources of…

Machine Learning · Statistics 2025-04-25 James McInerney , Nathan Kallus

Generalised Bayesian inference updates prior beliefs using a loss function, rather than a likelihood, and can therefore be used to confer robustness against possible mis-specification of the likelihood. Here we consider generalised Bayesian…

Methodology · Statistics 2022-01-12 Takuo Matsubara , Jeremias Knoblauch , François-Xavier Briol , Chris. J. Oates

Inverse problems arise anywhere we have indirect measurement. As, in general they are ill-posed, to obtain satisfactory solutions for them needs prior knowledge. Classically, different regularization methods and Bayesian inference based…

Machine Learning · Statistics 2023-08-31 Ali Mohammad-Djafari , Ning Chu , Li Wang , Liang Yu

Regularization is a common tool in variational inverse problems to impose assumptions on the parameters of the problem. One such assumption is sparsity, which is commonly promoted using lasso and total variation-like regularization.…

Statistics Theory · Mathematics 2023-02-15 Jasper Marijn Everink , Yiqiu Dong , Martin Skovgaard Andersen

Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximizing reward rather than sampling from the true Bayesian…

Machine Learning · Computer Science 2026-02-27 Daniel Geyfman , Felix Draxler , Jan Groeneveld , Hyunsoo Lee , Theofanis Karaletsos , Stephan Mandt

Neural networks are powerful function approximators with tremendous potential in learning complex distributions. However, they are prone to overfitting on spurious patterns. Bayesian inference provides a principled way to regularize neural…

Machine Learning · Computer Science 2024-12-02 Yanzhe Bekkemoen , Helge Langseth

In this paper, we study the learning rate of generalized Bayes estimators in a general setting where the hypothesis class can be uncountable and have an irregular shape, the loss function can have heavy tails, and the optimal hypothesis may…

Statistics Theory · Mathematics 2021-11-22 Lam Si Tung Ho , Binh T. Nguyen , Vu Dinh , Duy Nguyen

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