English
Related papers

Related papers: Beyond NNGP: Large Deviations and Feature Learning…

200 papers

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

Gaussian Processes (GPs) are widely seen as the state-of-the-art surrogate models for Bayesian optimization (BO) due to their ability to model uncertainty and their performance on tasks where correlations are easily captured (such as those…

Machine Learning · Computer Science 2024-12-13 Paul Brunzema , Mikkel Jordahn , John Willes , Sebastian Trimpe , Jasper Snoek , James Harrison

We propose a novel Bayesian neural network architecture that can learn invariances from data alone by inferring a posterior distribution over different weight-sharing schemes. We show that our model outperforms other non-invariant…

Machine Learning · Statistics 2021-11-04 Nikolaos Mourdoukoutas , Marco Federici , Georges Pantalos , Mark van der Wilk , Vincent Fortuin

We consider the problem of learning Bayesian network classifiers that maximize the marginover a set of classification variables. We find that this problem is harder for Bayesian networks than for undirected graphical models like maximum…

Machine Learning · Computer Science 2012-07-09 Yuhong Guo , Dana Wilkinson , Dale Schuurmans

Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data. We describe and study in these models a decomposition of predictive uncertainty into…

Machine Learning · Statistics 2017-11-15 Stefan Depeweg , José Miguel Hernández-Lobato , Finale Doshi-Velez , Steffen Udluft

Choosing appropriate hyperparameters plays a crucial role in the success of neural networks as hyper-parameters directly control the behavior and performance of the training algorithms. To obtain efficient tuning, Bayesian optimization…

Machine Learning · Statistics 2024-02-08 Jiazhao Zhang , Ying Hung , Chung-Ching Lin , Zicheng Liu

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

Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural networks, variational Bayes…

Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic gradient descent, we demonstrate explicitly Bayesian…

Machine Learning · Computer Science 2019-10-23 Xinjie Lan , Kenneth E. Barner

In this work, we advocate for the importance of singular learning theory (SLT) as it pertains to the theory and practice of variational inference in Bayesian neural networks (BNNs). To begin, using SLT, we lay to rest some of the confusion…

Machine Learning · Statistics 2023-02-14 Susan Wei , Edmund Lau

Probabilistic predictions from neural networks which account for predictive uncertainty during classification is crucial in many real-world and high-impact decision making settings. However, in practice most datasets are trained on…

Machine Learning · Computer Science 2022-09-30 Satya Borgohain , Klaus Ackermann , Ruben Loaiza-Maya

Gaussian processes (GPs) are nonparametric priors over functions. Fitting a GP implies computing a posterior distribution of functions consistent with the observed data. Similarly, deep Gaussian processes (DGPs) should allow us to compute a…

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

Neural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system. We propose a Bayesian version of N-ODEs that enables well-calibrated…

Machine Learning · Computer Science 2020-02-19 Andreas Look , Melih Kandemir

We introduce scalable algorithms for online learning of neural network parameters and Bayesian sequential decision making. Unlike classical Bayesian neural networks, which induce predictive uncertainty through a posterior over model…

Machine Learning · Computer Science 2025-10-10 Gerardo Duran-Martin , Leandro Sánchez-Betancourt , Álvaro Cartea , Kevin Murphy

Deep learning and convolutional neural networks in particular are powerful and promising tools for cosmological analysis of large-scale structure surveys. They are already providing similar performance to classical analysis methods using…

Cosmology and Nongalactic Astrophysics · Physics 2026-05-06 Gaspard Aymerich , Tomasz Kacprzak , Alexandre Refregier

We challenge the longstanding assumption that the mean-field approximation for variational inference in Bayesian neural networks is severely restrictive, and show this is not the case in deep networks. We prove several results indicating…

Machine Learning · Computer Science 2021-03-11 Sebastian Farquhar , Lewis Smith , Yarin Gal

In this work, we focus on variational Bayesian inference on the sparse Deep Neural Network (DNN) modeled under a class of spike-and-slab priors. Given a pre-specified sparse DNN structure, the corresponding variational posterior contraction…

Statistics Theory · Mathematics 2020-08-04 Jincheng Bai , Qifan Song , Guang Cheng

We here unify the field theoretical approach to neuronal networks with large deviations theory. For a prototypical random recurrent network model with continuous-valued units, we show that the effective action is identical to the rate…

Disordered Systems and Neural Networks · Physics 2021-10-13 Alexander van Meegen , Tobias Kühn , 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
‹ Prev 1 8 9 10 Next ›