English
Related papers

Related papers: Spectral Bias and Task-Model Alignment Explain Gen…

200 papers

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

Deep kernel learning provides an elegant and principled framework for combining the structural properties of deep learning algorithms with the flexibility of kernel methods. By means of a deep neural network, we learn a parametrized kernel…

Machine Learning · Computer Science 2020-12-14 Prudencio Tossou , Basile Dura , Francois Laviolette , Mario Marchand , Alexandre Lacoste

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent…

Machine Learning · Computer Science 2018-11-20 Farzan Farnia , Jesse M. Zhang , David Tse

We take a geometrical viewpoint and present a unifying view on supervised deep learning with the Bregman divergence loss function - this entails frequent classification and prediction tasks. Motivated by simulations we suggest that there is…

Machine Learning · Computer Science 2021-07-07 Petr Taborsky , Lars Kai Hansen

The primary hyperparameter in kernel regression (KR) is the choice of kernel. In most theoretical studies of KR, one assumes the kernel is fixed before seeing the training data. Under this assumption, it is known that the optimal kernel is…

Machine Learning · Computer Science 2022-09-28 James B. Simon

Much attention has been devoted recently to the generalization puzzle in deep learning: large, deep networks can generalize well, but existing theories bounding generalization error are exceedingly loose, and thus cannot explain this…

Machine Learning · Statistics 2019-01-08 Andrew K. Lampinen , Surya Ganguli

Several works have proposed Simplicity Bias (SB)---the tendency of standard training procedures such as Stochastic Gradient Descent (SGD) to find simple models---to justify why neural networks generalize well [Arpit et al. 2017, Nakkiran et…

Machine Learning · Computer Science 2020-10-29 Harshay Shah , Kaustav Tamuly , Aditi Raghunathan , Prateek Jain , Praneeth Netrapalli

The widely observed 'benign overfitting phenomenon' in the neural network literature raises the challenge to the 'bias-variance trade-off' doctrine in the statistical learning theory. Since the generalization ability of the 'lazy trained'…

Machine Learning · Computer Science 2023-09-26 Yicheng Li , Haobo Zhang , Qian Lin

Ensemble learning is traditionally justified as a variance-reduction strategy, explaining its strong performance for unstable predictors such as decision trees. This explanation, however, does not account for ensembles constructed from…

Machine Learning · Statistics 2025-12-30 Ernest Fokoué

Although statistical learning theory provides a robust framework to understand supervised learning, many theoretical aspects of deep learning remain unclear, in particular how different architectures may lead to inductive bias when trained…

Machine Learning · Computer Science 2024-03-27 Cédric Gerbelot , Avetik Karagulyan , Stefani Karp , Kavya Ravichandran , Menachem Stern , Nathan Srebro

In many modern applications of deep learning the neural network has many more parameters than the data points used for its training. Motivated by those practices, a large body of recent theoretical research has been devoted to studying…

Statistics Theory · Mathematics 2022-12-07 A. Tsigler , P. L. Bartlett

A fairly comprehensive analysis is presented for the gradient descent dynamics for training two-layer neural network models in the situation when the parameters in both layers are updated. General initialization schemes as well as general…

Machine Learning · Computer Science 2020-02-27 Weinan E , Chao Ma , Lei Wu

In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. In this setting, questions about data efficiency, memorization, generalization, and speed of learning can be studied in great…

Machine Learning · Computer Science 2022-01-07 Alethea Power , Yuri Burda , Harri Edwards , Igor Babuschkin , Vedant Misra

State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain…

Machine Learning · Statistics 2019-11-01 Alberto Bietti , Julien Mairal

Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what enables them to extract meaningful representations, or why…

Machine Learning · Statistics 2026-03-19 Nil Ayday , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar

It is a commonly held belief that enforcing invariance improves generalisation. Although this approach enjoys widespread popularity, it is only very recently that a rigorous theoretical demonstration of this benefit has been established. In…

Machine Learning · Statistics 2021-12-21 Bryn Elesedy

Benign overfitting is a phenomenon in machine learning where a model perfectly fits (interpolates) the training data, including noisy examples, yet still generalizes well to unseen data. Understanding this phenomenon has attracted…

Machine Learning · Computer Science 2025-05-20 Junhyung Park , Patrick Bloebaum , Shiva Prasad Kasiviswanathan

Data augmentation, a technique in which a training set is expanded with class-preserving transformations, is ubiquitous in modern machine learning pipelines. In this paper, we seek to establish a theoretical framework for understanding data…

Machine Learning · Computer Science 2019-03-21 Tri Dao , Albert Gu , Alexander J. Ratner , Virginia Smith , Christopher De Sa , Christopher Ré

By leveraging the kernel trick in the output space, kernel-induced losses provide a principled way to define structured output prediction tasks for a wide variety of output modalities. In particular, they have been successfully used in the…

Machine Learning · Statistics 2024-06-14 Tamim El Ahmad , Junjie Yang , Pierre Laforgue , Florence d'Alché-Buc

Understanding generalization of overparametrized neural networks remains a fundamental challenge in machine learning. Most of the literature mostly studies generalization from an interpolation point of view, taking convergence of parameters…

Machine Learning · Computer Science 2025-06-13 Etienne Boursier , Nicolas Flammarion