English
Related papers

Related papers: Understanding Generalization from Embedding Dimens…

200 papers

Modern neural networks are highly overparameterized, with capacity to substantially overfit to training data. Nevertheless, these networks often generalize well in practice. It has also been observed that trained networks can often be…

Machine Learning · Statistics 2019-02-26 Wenda Zhou , Victor Veitch , Morgane Austern , Ryan P. Adams , Peter Orbanz

Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance. To examine the structure of when and where memorization occurs in a deep network, we use a recently developed…

Machine Learning · Computer Science 2021-06-01 Cory Stephenson , Suchismita Padhy , Abhinav Ganesh , Yue Hui , Hanlin Tang , SueYeon Chung

Datasets such as images, text, or movies are embedded in high-dimensional spaces. However, in important cases such as images of objects, the statistical structure in the data constrains samples to a manifold of dramatically lower…

Machine Learning · Computer Science 2019-10-29 Stefano Recanatesi , Matthew Farrell , Madhu Advani , Timothy Moore , Guillaume Lajoie , Eric Shea-Brown

Recently, learning a model that generalizes well on out-of-distribution (OOD) data has attracted great attention in the machine learning community. In this paper, after defining OOD generalization via Wasserstein distance, we theoretically…

Machine Learning · Computer Science 2021-05-25 Mingyang Yi , Lu Hou , Jiacheng Sun , Lifeng Shang , Xin Jiang , Qun Liu , Zhi-Ming Ma

Algorithm unfolding or unrolling is the technique of constructing a deep neural network (DNN) from an iterative algorithm. Unrolled DNNs often provide better interpretability and superior empirical performance over standard DNNs in signal…

Machine Learning · Statistics 2024-02-21 Carter Lyons , Raghu G. Raj , Margaret Cheney

Why does training deep neural networks using stochastic gradient descent (SGD) result in a generalization error that does not worsen with the number of parameters in the network? To answer this question, we advocate a notion of effective…

Machine Learning · Computer Science 2019-01-15 Vaishnavh Nagarajan , J. Zico Kolter

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

Machine Learning · Computer Science 2026-04-10 Zeran Johannsen

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

Random features models play a distinguished role in the theory of deep learning, describing the behavior of neural networks close to their infinite-width limit. In this work, we present a thorough analysis of the generalization performance…

Disordered Systems and Neural Networks · Physics 2025-02-03 Fabián Aguirre-López , Silvio Franz , Mauro Pastore

Despite significant research on the optimization aspects of federated learning, the exploration of generalization error, especially in the realm of heterogeneous federated learning, remains an area that has been insufficiently investigated,…

Machine Learning · Statistics 2025-09-17 Saptarshi Chakraborty , Peter L. Bartlett

In this paper we show that the expected generalisation performance of a learning machine is determined by the distribution of risks or equivalently its logarithm -- a quantity we term the risk entropy -- and the fluctuations in a quantity…

Machine Learning · Computer Science 2022-02-16 Dominic Belcher , Antonia Marcu , Adam Prügel-Bennett

In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting. Time series do not satisfy the typical assumption in statistical learning theory of the data being…

Machine Learning · Statistics 2019-07-30 Anastasia Borovykh , Cornelis W. Oosterlee , Sander M. Bohte

Approximation and learning of classifiers of large data sets by neural networks in terms of high-dimensional geometry and statistical learning theory are investigated. The influence of the VC dimension of sets of input-output functions of…

Machine Learning · Statistics 2025-11-18 Vera Kurkova , Marcello Sanguineti

Recent results on optimization and generalization properties of neural networks showed that in a simple two-layer network, the alignment of the labels to the eigenvectors of the corresponding Gram matrix determines the convergence of the…

Machine Learning · Computer Science 2023-02-03 Arman Rahbar , Emilio Jorge , Devdatt Dubhashi , Morteza Haghir Chehreghani

Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population (e.g., all potential app users). This raises…

Machine Learning · Statistics 2026-02-09 Julian Rodemann , Unai Fischer-Abaigar , James Bailie , Krikamol Muandet

Understanding generalization in deep neural networks is an active area of research. A promising avenue of exploration has been that of margin measurements: the shortest distance to the decision boundary for a given sample or its…

Machine Learning · Computer Science 2023-08-30 Coenraad Mouton , Marthinus W. Theunissen , Marelie H. Davel

We study the notion of a generalization bound being uniformly tight, meaning that the difference between the bound and the population loss is small for all learning algorithms and all population distributions. Numerous generalization bounds…

Machine Learning · Computer Science 2023-11-29 Michael Gastpar , Ido Nachum , Jonathan Shafer , Thomas Weinberger

Machine learning models with inputs in a Euclidean space $\mathbb{R}^d$, when implemented on digital computers, generalize, and their generalization gap converges to $0$ at a rate of $c/N^{1/2}$ concerning the sample size $N$. However, the…

Machine Learning · Computer Science 2026-05-14 Anastasis Kratsios , A. Martina Neuman , Gudmund Pammer

Rapid progress in representation learning has led to a proliferation of embedding models, and to associated challenges of model selection and practical application. It is non-trivial to assess a model's generalizability to new, candidate…

Machine Learning · Computer Science 2022-02-18 Leo Betthauser , Urszula Chajewska , Maurice Diesendruck , Rohith Pesala

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks. Existing methods are devoted to developing various robust training strategies or regularizations to update the weights of the neural network. But beyond the weights, the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Minjing Dong , Yanxi Li , Yunhe Wang , Chang Xu