English
Related papers

Related papers: Random ReLU Neural Networks as Non-Gaussian Proces…

200 papers

Complex-valued signals are used in the modeling of many systems in engineering and science, hence being of fundamental interest. Often, random complex-valued signals are considered to be proper. A proper complex random variable or process…

Machine Learning · Computer Science 2015-02-19 Rafael Boloix-Tortosa , F. Javier Payán-Somet , Eva Arias-de-Reyna , Juan José Murillo-Fuentes

While deep neural networks (DNNs) have achieved remarkable performance in tasks such as image recognition, they often struggle with generalization, learning from few examples, and continuous adaptation - abilities inherent in biological…

Machine Learning · Computer Science 2026-03-04 Patrick Inoue , Florian Röhrbein , Andreas Knoblauch

A neural architecture with randomly initialized weights, in the infinite width limit, is equivalent to a Gaussian Random Field whose covariance function is the so-called Neural Network Gaussian Process kernel (NNGP). We prove that a…

Machine Learning · Computer Science 2024-04-29 Rustem Takhanov

When characterizing materials, it can be important to not only predict their mechanical properties, but also to estimate the probability distribution of these properties across a set of samples. Constitutive neural networks allow for the…

Computational Engineering, Finance, and Science · Computer Science 2025-03-18 Jeremy A. McCulloch , Ellen Kuhl

Various approaches to stochastic processes exist, noting that key properties such as measurability and continuity are not trivially satisfied. We introduce a new theory for Gaussian processes using improper linear functionals. Using a…

Statistics Theory · Mathematics 2020-10-15 Niels Lundtorp Olsen

Training large neural networks exposes neural scaling laws for the generalization error, which points to a universal behavior across network architectures of learning in high dimensions. It was also shown that this effect persists in the…

Disordered Systems and Neural Networks · Physics 2026-02-27 Jakob Kramp , Javed Lindner , Moritz Helias

This work analyzes Graph Neural Networks, a generalization of Fully-Connected Deep Neural Nets on Graph structured data, when their width, that is the number of nodes in each fullyconnected layer is increasing to infinity. Infinite Width…

Machine Learning · Computer Science 2023-11-21 Yunus Cobanoglu

Bayesian inference of nanohertz gravitational-wave background models in pulsar timing array analyses often relies on Gaussian-process interpolators to avoid repeated, computationally expensive strain-spectrum calculations. However,…

Cosmology and Nongalactic Astrophysics · Physics 2026-04-16 Shreyas Tiruvaskar , Chris Gordon

Marginalising out uncertain quantities within the internal representations or parameters of neural networks is of central importance for a wide range of learning techniques, such as empirical, variational or full Bayesian methods. We set…

Machine Learning · Statistics 2015-07-21 Justin Bayer , Maximilian Karl , Daniela Korhammer , Patrick van der Smagt

We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian…

Neural and Evolutionary Computing · Computer Science 2022-01-05 Stephen Whitelam , Viktor Selin , Sang-Won Park , Isaac Tamblyn

Gaussian process (GP) regression is a non-parametric, Bayesian framework to approximate complex models. Standard GP regression can lead to an unbounded model in which some points can take infeasible values. We introduce a new GP method that…

Machine Learning · Statistics 2024-04-04 Didem Kochan , Xiu Yang

Path regularization has shown to be a very effective regularization to train neural networks, leading to a better generalization property than common regularizations i.e. weight decay, etc. We propose a first near-complete (as will be made…

Machine Learning · Computer Science 2026-04-09 Hao Yu

Gaussian processes constitute a very powerful and well-understood method for non-parametric regression and classification. In the classical framework, the training data consists of deterministic vector-valued inputs and the corresponding…

Systems and Control · Computer Science 2018-09-26 Maxim Dolgov , Uwe D. Hanebeck

In this note, we develop semi-analytical techniques to obtain the full correlational structure of a stochastic network of nonlinear neurons described by rate variables. Under the assumption that pairs of membrane potentials are jointly…

Neurons and Cognition · Quantitative Biology 2016-10-12 Guillaume Hennequin , Máté Lengyel

The analysis of neural network training beyond their linearization regime remains an outstanding open question, even in the simplest setup of a single hidden-layer. The limit of infinitely wide networks provides an appealing route forward…

Machine Learning · Computer Science 2020-06-19 Jaume de Dios , Joan Bruna

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte

Bayesian neural networks attempt to combine the strong predictive performance of neural networks with formal quantification of uncertainty associated with the predictive output in the Bayesian framework. However, it remains unclear how to…

Machine Learning · Statistics 2022-01-12 Takuo Matsubara , Chris J. Oates , François-Xavier Briol

Deep learning relies on good initialization schemes and hyperparameter choices prior to training a neural network. Random weight initializations induce random network ensembles, which give rise to the trainability, training speed, and…

Machine Learning · Statistics 2019-10-25 Rebekka Burkholz , Alina Dubatovka

Nonparametric regression for massive numbers of samples (n) and features (p) is an increasingly important problem. In big n settings, a common strategy is to partition the feature space, and then separately apply simple models to each…

Machine Learning · Statistics 2014-06-10 Rajarshi Guhaniyogi , David B. Dunson

We present a probabilistic framework for nonlinearities, based on doubly truncated Gaussian distributions. By setting the truncation points appropriately, we are able to generate various types of nonlinearities within a unified framework,…

Machine Learning · Statistics 2017-09-20 Qinliang Su , Xuejun Liao , Lawrence Carin
‹ Prev 1 8 9 10 Next ›