English
Related papers

Related papers: Generalization error bounds for two-layer neural n…

200 papers

Providing generalization guarantees for modern neural networks has been a crucial task in statistical learning. Recently, several studies have attempted to analyze the generalization error in such settings by using tools from fractal…

Machine Learning · Statistics 2023-07-11 Benjamin Dupuis , George Deligiannidis , Umut Şimşekli

Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks. Since such bounds often hold uniformly over all parameters, they suffer from over-parametrization and fail to account…

Machine Learning · Statistics 2023-11-14 Songyan Hou , Parnian Kassraie , Anastasis Kratsios , Andreas Krause , Jonas Rothfuss

Deep neural networks often generalize well despite heavy over-parameterization, challenging classical parameter-based analyses. We study generalization from a representation-centric perspective and analyze how the geometry of learned…

Machine Learning · Computer Science 2026-02-02 Junjie Yu , Zhuoli Ouyang , Haotian Deng , Chen Wei , Wenxiao Ma , Jianyu Zhang , Zihan Deng , Quanying Liu

Using Stein's method techniques introduced by Chatterjee (2008) and further extended by Kasprzak and Peccati (2022) and by Lachi\`eze-Rey and Peccati (2017), we derive novel quantitative bounds on the convergence in distribution of…

Probability · Mathematics 2026-01-30 Lucia Celli

We prove an exponential size separation between depth 2 and depth 3 neural networks (with real inputs), when approximating a $\mathcal{O}(1)$-Lipschitz target function to constant accuracy, with respect to a distribution with support in the…

Machine Learning · Computer Science 2024-11-08 Itay Safran , Daniel Reichman , Paul Valiant

We study the training and generalization of deep neural networks (DNNs) in the over-parameterized regime, where the network width (i.e., number of hidden nodes per layer) is much larger than the number of training data points. We show that,…

Machine Learning · Computer Science 2019-11-13 Yuan Cao , Quanquan Gu

We consider information-theoretic bounds on expected generalization error for statistical learning problems in a networked setting. In this setting, there are $K$ nodes, each with its own independent dataset, and the models from each node…

Information Theory · Computer Science 2024-01-17 L. P. Barnes , Alex Dytso , H. V. Poor

We demonstrate that applying an eventual decay to the learning rate (LR) in empirical risk minimization (ERM), where the mean-squared-error loss is minimized using standard gradient descent (GD) for training a two-layer neural network with…

Machine Learning · Statistics 2026-02-10 Kyle Sung , Kholood Khalil , Noah Forman , Steven Samu , Anastasis Kratsios

In this work, we propose a novel generalized Wasserstein-2 distance approach for efficiently training stochastic neural networks to reconstruct random field models, where the target random variable comprises both continuous and categorical…

Machine Learning · Computer Science 2025-07-08 Mingtao Xia , Qijing Shen

We obtain explicit $p$-Wasserstein distance error bounds between the distribution of the multi-parameter MLE and the multivariate normal distribution. Our general bounds are given for possibly high-dimensional, independent and identically…

Statistics Theory · Mathematics 2021-12-28 Andreas Anastasiou , Robert E. Gaunt

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

Established approaches to obtain generalization bounds in data-driven optimization and machine learning mostly build on solutions from empirical risk minimization (ERM), which depend crucially on the functional complexity of the hypothesis…

Optimization and Control · Mathematics 2022-10-14 Yibo Zeng , Henry Lam

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very…

Machine Learning · Computer Science 2019-11-28 Yuan Cao , Quanquan Gu

Neural oscillators that originate from second-order ordinary differential equations (ODEs) have shown competitive performance in learning mappings between dynamic loads and responses of complex nonlinear structural systems. Despite this…

Machine Learning · Computer Science 2026-05-11 Zifeng Huang , Konstantin M. Zuev , Yong Xia , Michael Beer

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing…

Optimization and Control · Mathematics 2019-11-05 Lei Li

Generalization bounds which assess the difference between the true risk and the empirical risk, have been studied extensively. However, to obtain bounds, current techniques use strict assumptions such as a uniformly bounded or a Lipschitz…

Machine Learning · Computer Science 2022-11-03 Itai Gat , Yossi Adi , Alexander Schwing , Tamir Hazan

We study non-convex empirical risk minimization for learning halfspaces and neural networks. For loss functions that are $L$-Lipschitz continuous, we present algorithms to learn halfspaces and multi-layer neural networks that achieve…

Machine Learning · Computer Science 2015-11-26 Yuchen Zhang , Jason D. Lee , Martin J. Wainwright , Michael I. Jordan

The Lipschitz constant is an important quantity that arises in analysing the convergence of gradient-based optimization methods. It is generally unclear how to estimate the Lipschitz constant of a complex model. Thus, this paper studies an…

Machine Learning · Statistics 2023-02-10 Calypso Herrera , Florian Krach , Josef Teichmann

We establish generalization error bounds for stochastic gradient Langevin dynamics (SGLD) with constant learning rate under the assumptions of dissipativity and smoothness, a setting that has received increased attention in the…

Machine Learning · Statistics 2021-11-29 Tyler Farghly , Patrick Rebeschini

In this paper, we study data-dependent generalization error bounds exhibiting a mild dependency on the number of classes, making them suitable for multi-class learning with a large number of label classes. The bounds generally hold for…

Machine Learning · Computer Science 2018-01-01 Yunwen Lei , Urun Dogan , Ding-Xuan Zhou , Marius Kloft