中文
相关论文

相关论文: Student-t processes as infinite-width limits of po…

200 篇论文

Recent work has shown that the prior over functions induced by a deep Bayesian neural network (BNN) behaves as a Gaussian process (GP) as the width of all layers becomes large. However, many BNN applications are concerned with the BNN…

机器学习 · 统计学 2020-11-30 Jiri Hron , Yasaman Bahri , Roman Novak , Jeffrey Pennington , Jascha Sohl-Dickstein

Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of the favorable properties of Gaussian processes, this…

机器学习 · 计算机科学 2026-03-24 Steven Adams , Andrea Patanè , Morteza Lahijanian , Luca Laurenti

Gaussian processes are ubiquitous in nature and engineering. A case in point is a class of neural networks in the infinite-width limit, whose priors correspond to Gaussian processes. Here we perturbatively extend this correspondence to…

机器学习 · 统计学 2020-08-28 Sho Yaida

We establish novel rates for the Gaussian approximation of random deep neural networks with Gaussian parameters (weights and biases) and Lipschitz activation functions, in the wide limit. Our bounds apply for the joint output of a network…

统计理论 · 数学 2023-12-20 Dario Trevisan

In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence…

机器学习 · 统计学 2026-03-06 Eloy Mosig , Andrea Agazzi , Dario Trevisan

Bayesian neural networks (BNNs) combine the expressive power of deep learning with the advantages of Bayesian formalism. In recent years, the analysis of wide, deep BNNs has provided theoretical insight into their priors and posteriors.…

机器学习 · 计算机科学 2022-02-24 Beau Coker , Wessel P. Bruinsma , David R. Burt , Weiwei Pan , Finale Doshi-Velez

This article gives a new proof that fully connected neural networks with random weights and biases converge to Gaussian processes in the regime where the input dimension, output dimension, and depth are kept fixed, while the hidden layer…

概率论 · 数学 2021-07-06 Boris Hanin

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.…

机器学习 · 统计学 2021-11-30 Mariia Vladimirova , Julyan Arbel , Stéphane Girard

From the classical and influential works of Neal (1996), it is known that the infinite width scaling limit of a Bayesian neural network with one hidden layer is a Gaussian process, when the network weights have bounded prior variance.…

机器学习 · 统计学 2024-06-06 Jorge Loría , Anindya Bhadra

We study the extent to which wide neural networks may be approximated by Gaussian processes when initialized with random weights. It is a well-established fact that as the width of a network goes to infinity, its law converges to that of a…

概率论 · 数学 2021-02-18 Ronen Eldan , Dan Mikulincer , Tselil Schramm

Despite its long history, Bayesian neural networks (BNNs) and variational training remain underused in practice: standard Gaussian posteriors misalign with network geometry, KL terms can be brittle in high dimensions, and implementations…

机器学习 · 计算机科学 2025-09-09 Carlos Stein Brito

There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not…

机器学习 · 统计学 2020-07-07 Devanshu Agrawal , Theodore Papamarkou , Jacob Hinkle

Bayesian approaches for training deep neural networks (BNNs) have received significant interest and have been effectively utilized in a wide range of applications. There have been several studies on the properties of posterior…

机器学习 · 统计学 2024-03-22 Insung Kong , Yongdai Kim

We study quantum neural networks where the generated function is the expectation value of the sum of single-qubit observables across all qubits. In [Girardi \emph{et al.}, arXiv:2402.08726], it is proven that the probability distributions…

Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires either some heuristics to sample a batch of design points at one…

机器学习 · 计算机科学 2020-01-28 Evgenii Tsymbalov , Sergei Makarychev , Alexander Shapeev , Maxim Panov

There has been a recent surge of interest in modeling neural networks (NNs) as Gaussian processes. In the limit of a NN of infinite width the NN becomes equivalent to a Gaussian process. Here we demonstrate that for an ensemble of large,…

机器学习 · 计算机科学 2019-08-28 Joseph M. Antognini

Gaussian Process is a non-parametric prior which can be understood as a distribution on the function space intuitively. It is known that by introducing appropriate prior to the weights of the neural networks, Gaussian Process can be…

机器学习 · 统计学 2021-01-08 Erdong Guo , David Draper

In this work, we study scaling limits of shallow Bayesian neural networks (BNNs) via their connection to Gaussian processes (GPs), with an emphasis on statistical modeling, identifiability, and scalable inference. We first establish a…

机器学习 · 统计学 2026-02-27 Gracielle Antunes de Araújo , Flávio B. Gonçalves

We present a new method to approximate posterior probabilities of Bayesian Network using Deep Neural Network. Experiment results on several public Bayesian Network datasets shows that Deep Neural Network is capable of learning joint…

机器学习 · 计算机科学 2018-01-12 Jie Jia , Honggang Zhou , Yunchun Li

A Bayesian treatment can mitigate overconfidence in ReLU nets around the training data. But far away from them, ReLU Bayesian neural networks (BNNs) can still underestimate uncertainty and thus be asymptotically overconfident. This issue…

机器学习 · 计算机科学 2022-01-25 Agustinus Kristiadi , Matthias Hein , Philipp Hennig
‹ 上一页 1 2 3 10 下一页 ›