English
Related papers

Related papers: Non-Vacuous Generalisation Bounds for Shallow Neur…

200 papers

Both PAC-Bayesian and Sample Compress learning frameworks are instrumental for deriving tight (non-vacuous) generalization bounds for neural networks. We leverage these results in a meta-learning scheme, relying on a hypernetwork that…

Machine Learning · Computer Science 2025-06-06 Benjamin Leblanc , Mathieu Bazinet , Nathaniel D'Amours , Alexandre Drouin , Pascal Germain

We consider shallow (single hidden layer) neural networks and characterize their performance when trained with stochastic gradient descent as the number of hidden units $N$ and gradient descent steps grow to infinity. In particular, we…

Machine Learning · Statistics 2022-06-02 Jiahui Yu , Konstantinos Spiliopoulos

In this note we consider setups in which variational objectives for Bayesian neural networks can be computed in closed form. In particular we focus on single-layer networks in which the activation function is piecewise polynomial (e.g.…

Machine Learning · Statistics 2018-12-04 Martin Jankowiak

The primary objective of learning methods is generalization. Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep…

Machine Learning · Computer Science 2025-03-07 Lijia Yu , Yibo Miao , Yifan Zhu , Xiao-Shan Gao , Lijun Zhang

Neural operators generalize neural networks to learn mappings between function spaces from data. They are commonly used to learn solution operators of parametric partial differential equations (PDEs) or propagators of time-dependent PDEs.…

Machine Learning · Computer Science 2025-02-03 Emilia Magnani , Marvin Pförtner , Tobias Weber , Philipp Hennig

We study the dynamics and implicit bias of gradient flow (GF) on univariate ReLU neural networks with a single hidden layer in a binary classification setting. We show that when the labels are determined by the sign of a target network with…

Machine Learning · Computer Science 2023-02-03 Itay Safran , Gal Vardi , Jason D. Lee

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu

We give a general recipe for derandomising PAC-Bayesian bounds using margins, with the critical ingredient being that our randomised predictions concentrate around some value. The tools we develop straightforwardly lead to margin bounds for…

Machine Learning · Computer Science 2022-02-24 Felix Biggs , Benjamin Guedj

Neural networks are regularly employed in adaptive control of nonlinear systems and related methods of reinforcement learning. A common architecture uses a neural network with a single hidden layer (i.e. a shallow network), in which the…

Optimization and Control · Mathematics 2024-04-18 Andrew Lamperski , Tyler Lekang

Early-exit neural networks enable adaptive computation by allowing confident predictions to exit at intermediate layers, achieving 2-8$\times$ inference speedup. Despite widespread deployment, their generalization properties lack…

Machine Learning · Computer Science 2026-04-20 Dongxin Guo , Jikun Wu , Siu Ming Yiu

This paper provides rigorous error bounds for physics-informed neural networks approximating the semilinear wave equation. We provide bounds for the generalization and training error in terms of the width of the network's layers and the…

Numerical Analysis · Mathematics 2026-03-30 Beatrice Lorenz , Aras Bacho , Gitta Kutyniok

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. We consider the problem of learning a one hidden layer convolutional neural network with ReLU activation…

Optimization and Control · Mathematics 2020-02-26 Thu Dinh , Jack Xin

We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory. Our contributions are twofold: (i) we develop an end-to-end framework to train a binary activated deep neural…

Machine Learning · Computer Science 2020-02-05 Gaël Letarte , Pascal Germain , Benjamin Guedj , François Laviolette

Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measurements. By allowing a wide range of degrees of weight-sharing…

Machine Learning · Computer Science 2022-01-19 Ekkehard Schnoor , Arash Behboodi , Holger Rauhut

Recurrent Neural Networks (RNNs) have achieved great success in the prediction of sequential data. However, their theoretical studies are still lagging behind because of their complex interconnected structures. In this paper, we establish a…

Machine Learning · Statistics 2024-11-06 Xuewei Cheng , Ke Huang , Shujie Ma

This note examines the behavior of generalization capabilities - as defined by out-of-sample mean squared error (MSE) - of Linear Gaussian (with a fixed design matrix) and Linear Least Squares regression. Particularly, we consider a…

Statistics Theory · Mathematics 2021-09-21 Karthik Duraisamy

Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model. In this paper, we study how equivariance relates to generalization error utilizing PAC Bayesian analysis…

Machine Learning · Computer Science 2022-10-25 Arash Behboodi , Gabriele Cesa , Taco Cohen

In this paper, we derive a PAC-Bayes bound on the generalisation gap, in a supervised time-series setting for a special class of discrete-time non-linear dynamical systems. This class includes stable recurrent neural networks (RNN), and the…

Machine Learning · Computer Science 2024-04-12 Deividas Eringis , John Leth , Zheng-Hua Tan , Rafal Wisniewski , Mihaly Petreczky

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.…

Machine Learning · Statistics 2024-06-06 Jorge Loría , Anindya Bhadra

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