English
Related papers

Related papers: Bayesian Deep Ensembles via the Neural Tangent Ker…

200 papers

We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples using theoretical methods from Gaussian processes and statistical physics. Our expressions apply to…

Machine Learning · Computer Science 2021-02-26 Blake Bordelon , Abdulkadir Canatar , Cengiz Pehlevan

The gamma belief network (GBN), often regarded as a deep topic model, has demonstrated its potential for uncovering multi-layer interpretable latent representations in text data. Its notable capability to acquire interpretable latent…

Machine Learning · Computer Science 2024-08-16 Zhibin Duan , Tiansheng Wen , Muyao Wang , Bo Chen , Mingyuan Zhou

In Continual Learning settings, deep neural networks are prone to Catastrophic Forgetting. Orthogonal Gradient Descent was proposed to tackle the challenge. However, no theoretical guarantees have been proven yet. We present a theoretical…

Machine Learning · Statistics 2020-12-07 Mehdi Abbana Bennani , Thang Doan , Masashi Sugiyama

Small generalization errors of over-parameterized neural networks (NNs) can be partially explained by the frequency biasing phenomenon, where gradient-based algorithms minimize the low-frequency misfit before reducing the high-frequency…

Machine Learning · Computer Science 2022-09-27 Annan Yu , Yunan Yang , Alex Townsend

Inference in popular nonparametric Bayesian models typically relies on sampling or other approximations. This paper presents a general methodology for constructing novel tractable nonparametric Bayesian methods by applying the kernel trick…

Machine Learning · Statistics 2011-08-15 Ferenc Huszár , Simon Lacoste-Julien

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to…

Machine Learning · Statistics 2024-03-04 Lingyu Gu , Yongqi Du , Yuan Zhang , Di Xie , Shiliang Pu , Robert C. Qiu , Zhenyu Liao

Graph neural networks (GNNs) continue to achieve state-of-the-art performance on many graph learning tasks, but rely on the assumption that a given graph is a sufficient approximation of the true neighborhood structure. When a system…

Machine Learning · Computer Science 2023-02-08 Steven J. Krieg , William C. Burgis , Patrick M. Soga , Nitesh V. Chawla

The posterior over Bayesian neural network (BNN) parameters is extremely high-dimensional and non-convex. For computational reasons, researchers approximate this posterior using inexpensive mini-batch methods such as mean-field variational…

Machine Learning · Computer Science 2021-04-30 Pavel Izmailov , Sharad Vikram , Matthew D. Hoffman , Andrew Gordon Wilson

Deep feedforward neural networks (DFNNs) are a powerful tool for functional approximation. We describe flexible versions of generalized linear and generalized linear mixed models incorporating basis functions formed by a DFNN. The…

Computation · Statistics 2018-05-28 Minh-Ngoc Tran , Nghia Nguyen , David Nott , Robert Kohn

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

Machine Learning · Statistics 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz

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…

Statistics Theory · Mathematics 2023-12-20 Dario Trevisan

While Gaussian processes (GPs) are the method of choice for regression tasks, they also come with practical difficulties, as inference cost scales cubic in time and quadratic in memory. In this paper, we introduce a natural and expressive…

Machine Learning · Computer Science 2018-09-13 Martin Trapp , Robert Peharz , Carl E. Rasmussen , Franz Pernkopf

We undertake Bayesian learning of the high-dimensional functional relationship between a system parameter vector and an observable, that is in general tensor-valued. The ultimate aim is Bayesian inverse prediction of the system parameters,…

Methodology · Statistics 2018-04-17 Kangrui Wang , Dalia Chakrabarty

We consider the optimal approximate posterior over the top-layer weights in a Bayesian neural network for regression, and show that it exhibits strong dependencies on the lower-layer weights. We adapt this result to develop a correlated…

Machine Learning · Statistics 2021-06-23 Sebastian W. Ober , Laurence Aitchison

Ensemble learning is a mainstay in modern data science practice. Conventional ensemble algorithms assign to base models a set of deterministic, constant model weights that (1) do not fully account for individual models' varying accuracy…

Methodology · Statistics 2019-04-02 Jeremiah Zhe Liu , John Paisley , Marianthi-Anna Kioumourtzoglou , Brent A. Coull

We propose a method (TT-GP) for approximate inference in Gaussian Process (GP) models. We build on previous scalable GP research including stochastic variational inference based on inducing inputs, kernel interpolation, and structure…

Machine Learning · Computer Science 2018-01-18 Pavel Izmailov , Alexander Novikov , Dmitry Kropotov

Neural-network-based machine learning interatomic potentials have emerged as powerful tools for predicting atomic energies and forces, enabling accurate and efficient simulations in atomistic modeling. A key limitation of traditional deep…

Chemical Physics · Physics 2025-09-24 Riccardo Farris , Emanuele Telari , Nongnuch Artrith , Konstantin Neyman , Albert Bruix

Deep kernel learning (DKL) and related techniques aim to combine the representational power of neural networks with the reliable uncertainty estimates of Gaussian processes. One crucial aspect of these models is an expectation that, because…

Machine Learning · Statistics 2021-07-08 Sebastian W. Ober , Carl E. Rasmussen , Mark van der Wilk

We rigorously analyse fully-trained neural networks of arbitrary depth in the Bayesian optimal setting in the so-called proportional scaling regime where the number of training samples and width of the input and all inner layers diverge…

Statistics Theory · Mathematics 2025-05-07 Francesco Camilli , Daria Tieplova , Eleonora Bergamin , Jean Barbier

Gaussian processes (GPs) are powerful and widely used probabilistic regression models, but their effectiveness in practice is often limited by the choice of kernel function. This kernel function is typically handcrafted from a small set of…

Machine Learning · Computer Science 2026-02-13 Jihao Andreas Lin , Sebastian Ament , Louis C. Tiao , David Eriksson , Maximilian Balandat , Eytan Bakshy