中文
相关论文

相关论文: On the Convergence of Locally Adaptive and Scalabl…

200 篇论文

Although linear regression models are fundamental tools in statistical science, the estimation results can be sensitive to outliers. While several robust methods have been proposed in frequentist frameworks, statistical inference is not…

统计方法学 · 统计学 2020-07-15 Shintaro Hashimoto , Shonosuke Sugasawa

Recent advances in reconstruction methods for inverse problems leverage powerful data-driven models, e.g., deep neural networks. These techniques have demonstrated state-of-the-art performances for several imaging tasks, but they often do…

计算机视觉与模式识别 · 计算机科学 2020-10-20 Riccardo Barbano , Chen Zhang , Simon Arridge , Bangti Jin

While Bayesian neural networks (BNNs) hold the promise of being flexible, well-calibrated statistical models, inference often requires approximations whose consequences are poorly understood. We study the quality of common variational…

机器学习 · 统计学 2020-10-26 Andrew Y. K. Foong , David R. Burt , Yingzhen Li , Richard E. Turner

Bayesian inference for neural networks, or Bayesian deep learning, has the potential to provide well-calibrated predictions with quantified uncertainty and robustness. However, the main hurdle for Bayesian deep learning is its computational…

机器学习 · 统计学 2023-09-07 Sanket Jantre , Nathan M. Urban , Xiaoning Qian , Byung-Jun Yoon

This paper proposes a sparse Bayesian treatment of deep neural networks (DNNs) for system identification. Although DNNs show impressive approximation ability in various fields, several challenges still exist for system identification…

系统与控制 · 电气工程与系统科学 2022-06-02 Hongpeng Zhou , Chahine Ibrahim , Wei Xing Zheng , Wei Pan

Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is…

Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-of-distribution or adversarially generated points. In this…

机器学习 · 计算机科学 2022-05-06 Kirill Fedyanin , Evgenii Tsymbalov , Maxim Panov

Deep neural networks (DNNs) have made a revolution in numerous fields during the last decade. However, in tasks with high safety requirements, such as medical or autonomous driving applications, providing an assessment of the models…

机器学习 · 计算机科学 2020-11-20 Omer Achrack , Raizy Kellerman , Ouriel Barzilay

Uncertainty quantification is essential when dealing with ill-conditioned inverse problems due to the inherent nonuniqueness of the solution. Bayesian approaches allow us to determine how likely an estimation of the unknown parameters is…

机器学习 · 统计学 2020-01-16 Ali Siahkoohi , Gabrio Rizzuti , Felix J. Herrmann

Uncertainty quantification plays an important role in achieving trustworthy and reliable learning-based computational imaging. Recent advances in generative modeling and Bayesian neural networks have enabled the development of…

图像与视频处理 · 电气工程与系统科学 2025-10-07 Canberk Ekmekci , Mujdat Cetin

In recent times, neural networks have become a powerful tool for the analysis of complex and abstract data models. However, their introduction intrinsically increases our uncertainty about which features of the analysis are model-related…

机器学习 · 统计学 2020-11-09 Tom Charnock , Laurence Perreault-Levasseur , François Lanusse

Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such…

机器学习 · 统计学 2018-05-28 Nick Pawlowski , Andrew Brock , Matthew C. H. Lee , Martin Rajchl , Ben Glocker

We propose a Monte Carlo algorithm to sample from high dimensional probability distributions that combines Markov chain Monte Carlo and importance sampling. We provide a careful theoretical analysis, including guarantees on robustness to…

统计计算 · 统计学 2019-09-18 Giacomo Zanella , Gareth Roberts

We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of…

机器学习 · 计算机科学 2023-11-14 Erik Lien Bolager , Iryna Burak , Chinmay Datar , Qing Sun , Felix Dietrich

We develop a novel deep learning method for uncertainty quantification in stochastic partial differential equations based on Bayesian neural network (BNN) and Hamiltonian Monte Carlo (HMC). A BNN efficiently learns the posterior…

机器学习 · 统计学 2022-10-24 Jeahan Jung , Minseok Choi

We define an evolving in-time Bayesian neural network called a Hidden Markov Neural Network, which addresses the crucial challenge in time-series forecasting and continual learning: striking a balance between adapting to new data and…

机器学习 · 统计学 2025-01-17 Lorenzo Rimella , Nick Whiteley

Model comparison for the purposes of selection, averaging and validation is a problem found throughout statistics. Within the Bayesian paradigm, these problems all require the calculation of the posterior probabilities of models within a…

统计方法学 · 统计学 2015-06-08 Yan Zhou , Adam M Johansen , John A D Aston

Bayesian Neural Networks represent a fascinating confluence of deep learning and probabilistic reasoning, offering a compelling framework for understanding uncertainty in complex predictive models. In this paper, we investigate the use of…

机器学习 · 计算机科学 2025-03-11 Lucia Pezzetti , Stefano Favaro , Stefano Peluchetti

We propose to use techniques from Bayesian inference and deep neural networks to translate uncertainty in seismic imaging to uncertainty in tasks performed on the image, such as horizon tracking. Seismic imaging is an ill-posed inverse…

地球物理 · 物理学 2022-06-17 Ali Siahkoohi , Gabrio Rizzuti , Felix J. Herrmann

Neural networks are popular state-of-the-art models for many different tasks.They are often trained via back-propagation to find a value of the weights that correctly predicts the observed data. Although back-propagation has shown good…

机器学习 · 统计学 2020-12-29 Simón Rodríguez Santana , Daniel Hernández-Lobato