English
Related papers

Related papers: Exact Gap between Generalization Error and Uniform…

200 papers

Classical statistical learning theory predicts a U-shaped relationship between test loss and model capacity, driven by the bias-variance trade-off. Recent advances in modern machine learning have revealed a more complex pattern,…

Machine Learning · Statistics 2026-04-23 Yin Liu , Jianwen Cai , Didong Li

Most modern learning problems are over-parameterized, where the number of learnable parameters is much greater than the number of training data points. In this over-parameterized regime, the training loss typically has infinitely many…

Machine Learning · Computer Science 2025-06-23 Kanumuri Nithin Varma , Babak Hassibi

We provide finite-sample distribution approximations, that are uniform in the parameter, for inference in linear mixed models. Focus is on variances and covariances of random effects in cases where existing theory fails because their…

Statistics Theory · Mathematics 2025-07-29 Karl Oskar Ekvall , Matteo Bottai

We study the generalization error of functions that interpolate prescribed data points and are selected by minimizing a weighted norm. Under natural and general conditions, we prove that both the interpolants and their generalization errors…

Numerical Analysis · Mathematics 2021-02-11 Weilin Li

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

We define a notion of general uniform interpolant, generalizing the notions of cover and of uniform interpolant and identify situations in which symbol elimination can be used for computing general uniform interpolants. We investigate the…

Logic in Computer Science · Computer Science 2025-06-03 Viorica Sofronie-Stokkermans

In this work we establish an algorithm and distribution independent non-asymptotic trade-off between the model size, excess test loss, and training loss of linear predictors. Specifically, we show that models that perform well on the test…

Machine Learning · Statistics 2023-04-20 Nikhil Ghosh , Mikhail Belkin

Background. A main theoretical puzzle is why over-parameterized Neural Networks (NNs) generalize well when trained to zero loss (i.e., so they interpolate the data). Usually, the NN is trained with Stochastic Gradient Descent (SGD) or one…

Machine Learning · Computer Science 2025-02-18 Gon Buzaglo , Itamar Harel , Mor Shpigel Nacson , Alon Brutzkus , Nathan Srebro , Daniel Soudry

This dissertation studies a fundamental open challenge in deep learning theory: why do deep networks generalize well even while being overparameterized, unregularized and fitting the training data to zero error? In the first part of the…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan

In this manuscript we consider the problem of generalized linear estimation on Gaussian mixture data with labels given by a single-index model. Our first result is a sharp asymptotic expression for the test and training errors in the…

Statistics Theory · Mathematics 2023-02-20 Luca Pesce , Florent Krzakala , Bruno Loureiro , Ludovic Stephan

Objective: This paper proposes a framework to support the scientific research of standards so that they can be better measured, evaluated, and designed. Methods: Beginning with the notion of common models, the framework describes the…

Other Computer Science · Computer Science 2023-08-17 Enrico Coiera

Motivated by surprisingly good generalization properties of learned deep neural networks in overparameterized scenarios and by the related double descent phenomenon, this paper analyzes the relation between smoothness and low generalization…

Machine Learning · Computer Science 2021-10-29 Yuege Xie , Hung-Hsu Chou , Holger Rauhut , Rachel Ward

The generalization error of a learning algorithm refers to the discrepancy between the loss of a learning algorithm on training data and that on unseen testing data. Various information-theoretic bounds on the generalization error have been…

Information Theory · Computer Science 2025-06-24 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

We study quantum algorithms for verifying properties of the output probability distribution of a classical or quantum circuit, given access to the source code that generates the distribution. We consider the basic task of uniformity…

Quantum Physics · Physics 2024-11-08 Clément L. Canonne , Robin Kothari , Ryan O'Donnell

In this paper, we explore bounds on the expected risk when using deep neural networks for supervised classification from an information theoretic perspective. Firstly, we introduce model risk and fitting error, which are derived from…

Machine Learning · Computer Science 2024-10-08 Binchuan Qi

Error bounds, which refer to inequalities that bound the distance of vectors in a test set to a given set by a residual function, have proven to be extremely useful in analyzing the convergence rates of a host of iterative methods for…

Optimization and Control · Mathematics 2015-12-14 Zirui Zhou , Anthony Man-Cho So

We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating the training data. In particular, we consider simple…

Machine Learning · Statistics 2022-06-17 Chen Cheng , John Duchi , Rohith Kuditipudi

The problem of convergence of moments of a sequence of random variables to the moments of its asymptotic distribution is important in many applications. These include the determination of the optimal training sample size in the cross…

Probability · Mathematics 2018-06-14 Georgios Afendras , Marianthi Markatou

For the last two decades, high-dimensional data and methods have proliferated throughout the literature. Yet, the classical technique of linear regression has not lost its usefulness in applications. In fact, many high-dimensional…

Statistics Theory · Mathematics 2021-05-18 Arun Kumar Kuchibhotla , Lawrence D. Brown , Andreas Buja , Edward I. George , Linda Zhao

A central problem in Binary Hypothesis Testing (BHT) is to determine the optimal tradeoff between the Type I error (referred to as false alarm) and Type II (referred to as miss) error. In this context, the exponential rate of convergence of…

Information Theory · Computer Science 2021-11-29 Sebastian Espinosa , Jorge F. Silva , Pablo Piantanida