English
Related papers

Related papers: Tight Generalization Bounds for Large-Margin Halfs…

200 papers

We present a general approach, based on exponential inequalities, to derive bounds on the generalization error of randomized learning algorithms. Using this approach, we provide bounds on the average generalization error as well as bounds…

Machine Learning · Computer Science 2023-03-10 Fredrik Hellström , Giuseppe Durisi

Nearest neighbor cells in $R^d,d\in\mathbb{N}$, are used to define coefficients of divergence ($\phi$-divergences) between continuous multivariate samples. For large sample sizes, such distances are shown to be asymptotically normal with a…

Probability · Mathematics 2009-03-06 Yu. Baryshnikov , Mathew D. Penrose , J. E. Yukich

Deep neural networks generalize well despite being heavily overparameterized, in apparent contradiction with classical learning theory based on uniform convergence over fixed hypothesis spaces. Uniform bounds over the entire parameter space…

Machine Learning · Statistics 2026-05-15 Hubert Leroux , Jean Marcus , Julien Roger

We present a series of new and more favorable margin-based learning guarantees that depend on the empirical margin loss of a predictor. We give two types of learning bounds, both distribution-dependent and valid for general families, in…

Machine Learning · Computer Science 2020-10-30 Corinna Cortes , Mehryar Mohri , Ananda Theertha Suresh

We derive generalization bounds for learning algorithms based on their robustness: the property that if a testing sample is "similar" to a training sample, then the testing error is close to the training error. This provides a novel…

Machine Learning · Computer Science 2015-03-17 Huan Xu , Shie Mannor

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L_2 regularization: We introduce the \gamma-adapted-dimension, which is a simple function of the spectrum of a…

Machine Learning · Computer Science 2015-03-17 Sivan Sabato , Nathan Srebro , Naftali Tishby

Recent research has made significant progress on the problem of bounding log partition functions for exponential family graphical models. Such bounds have associated dual parameters that are often used as heuristic estimates of the marginal…

Machine Learning · Computer Science 2012-07-19 Pradeep Ravikumar , John Lafferty

We consider bounds on the generalization performance of the least-norm linear regressor, in the over-parameterized regime where it can interpolate the data. We describe a sense in which any generalization bound of a type that is commonly…

Machine Learning · Statistics 2021-10-19 Peter L. Bartlett , Philip M. Long

We study the problem of PAC learning $\gamma$-margin halfspaces with Random Classification Noise. We establish an information-computation tradeoff suggesting an inherent gap between the sample complexity of the problem and the sample…

Machine Learning · Computer Science 2023-06-29 Ilias Diakonikolas , Jelena Diakonikolas , Daniel M. Kane , Puqian Wang , Nikos Zarifis

The following problem is considered: given a joint distribution $P_{XY}$ and an event $E$, bound $P_{XY}(E)$ in terms of $P_XP_Y(E)$ (where $P_XP_Y$ is the product of the marginals of $P_{XY}$) and a measure of dependence of $X$ and $Y$.…

Information Theory · Computer Science 2019-03-12 Ibrahim Issa , Amedeo Roberto Esposito , Michael Gastpar

Error bounds are central objects in optimization theory and its applications. They were for a long time restricted only to the theory before becoming over the course of time a field of itself. This paper is devoted to the study of error…

Optimization and Control · Mathematics 2023-11-17 Zhou Wei , Michel Théra , Jen-Chih Yao

Optimization seeks extremal points in a function. When there are superextensively many optima, optimization algorithms are liable to get stuck. Under these conditions, generic algorithms tend to find marginal optima, which have many nearly…

Disordered Systems and Neural Networks · Physics 2024-07-25 Jaron Kent-Dobias

Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory. While the total variation distance appears naturally in the sample complexity of distribution learning, it is analytically…

Probability · Mathematics 2022-03-11 Sami Davies , Arya Mazumdar , Soumyabrata Pal , Cyrus Rashtchian

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

We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that…

Machine Learning · Statistics 2022-07-08 Inbar Seroussi , Ofer Zeitouni

We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation bounds via the PAC-Bayes theory. These provide state-of-the-art guarantees on a number of classification…

Machine Learning · Computer Science 2022-10-21 Felix Biggs , Valentina Zantedeschi , Benjamin Guedj

This paper explores the generalization characteristics of iterative learning algorithms with bounded updates for non-convex loss functions, employing information-theoretic techniques. Our key contribution is a novel bound for the…

Machine Learning · Computer Science 2023-10-17 Jingwen Fu , Nanning Zheng

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

The first result in this paper provides a very general $\epsilon$-removal argument for the multilinear restriction estimate. The second result provides a refinement of the multilinear restriction estimate in the case when some terms have…

Classical Analysis and ODEs · Mathematics 2019-12-17 Ioan Bejenaru

While PAC-Bayes is now an established learning framework for light-tailed losses (\emph{e.g.}, subgaussian or subexponential), its extension to the case of heavy-tailed losses remains largely uncharted and has attracted a growing interest…

Machine Learning · Statistics 2023-04-25 Maxime Haddouche , Benjamin Guedj
‹ Prev 1 3 4 5 6 7 10 Next ›