English
Related papers

Related papers: Concentration inequalities for leave-one-out cross…

200 papers

Theoretical developments on cross validation (CV) have mainly focused on selecting one among a list of finite-dimensional models (e.g., subset or order selection in linear regression) or selecting a smoothing parameter (e.g., bandwidth for…

Statistics Theory · Mathematics 2008-12-18 Yuhong Yang

We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI). Contrary to other CMI bounds, which are black-box bounds that do not…

Machine Learning · Computer Science 2022-07-04 Mohamad Rida Rammal , Alessandro Achille , Aditya Golatkar , Suhas Diggavi , Stefano Soatto

Certifiable robustness gives the guarantee that small perturbations around an input to a classifier will not change the prediction. There are two approaches to provide certifiable robustness to adversarial examples: a) explicitly training…

Machine Learning · Computer Science 2025-08-04 Meiyu Zhong , Ravi Tandon

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured…

Machine Learning · Computer Science 2022-01-13 Aounon Kumar , Tom Goldstein

In computational social science, researchers often use a pre-trained, black box classifier to estimate the frequency of each class in unlabeled datasets. A variety of prevalence estimation techniques have been developed in the literature,…

Social and Information Networks · Computer Science 2024-04-03 Siqi Wu , Paul Resnick

Regular sound correspondences constitute the principal evidence in historical language comparison. Despite the heuristic focus on regularity, it is often more an intuitive judgement than a quantified evaluation, and irregularity is more…

Computation and Language · Computer Science 2026-02-03 Frederic Blum , Johann-Mattis List

Cross-Validation (CV) is the default choice for evaluating the performance of machine learning models. Despite its wide usage, their statistical benefits have remained half-understood, especially in challenging nonparametric regimes. In…

Statistics Theory · Mathematics 2024-08-22 Garud Iyengar , Henry Lam , Tianyu Wang

This paper is devoted to the estimators of the mean that provide strong non-asymptotic guarantees under minimal assumptions on the underlying distribution. The main ideas behind proposed techniques are based on bridging the notions of…

Statistics Theory · Mathematics 2019-05-07 Stanislav Minsker

We present a detailed study of estimation errors in terms of surrogate loss estimation errors. We refer to such guarantees as $\mathscr{H}$-consistency estimation error bounds, since they account for the hypothesis set $\mathscr{H}$…

Machine Learning · Computer Science 2022-05-18 Pranjal Awasthi , Anqi Mao , Mehryar Mohri , Yutao Zhong

We derive sufficient conditions for a probability measure on a finite product space (a spin system) to satisfy a (modified) logarithmic Sobolev inequality. We establish these conditions for various examples, such as the (vertex-weighted)…

Probability · Mathematics 2020-05-15 Holger Sambale , Arthur Sinulis

In this paper, we study problem of estimating a sparse regression vector with correct support in the presence of outlier samples. The inconsistency of lasso-type methods is well known in this scenario. We propose a combinatorial version of…

Machine Learning · Computer Science 2023-06-23 Adarsh Barik , Jean Honorio

We investigate generically applicable and intuitively appealing prediction intervals based on $k$-fold cross validation. We focus on the conditional coverage probability of the proposed intervals, given the observations in the training…

Statistics Theory · Mathematics 2022-05-13 Lukas Steinberger , Hannes Leeb

Cross-validation (CV) is a technique for evaluating the ability of statistical models/learning systems based on a given data set. Despite its wide applicability, the rather heavy computational cost can prevent its use as the system size…

Machine Learning · Statistics 2016-10-26 Yoshiyuki Kabashima , Tomoyuki Obuchi , Makoto Uemura

This paper investigates the efficiency of the K-fold cross-validation (CV) procedure and a debiased version thereof as a means of estimating the generalization risk of a learning algorithm. We work under the general assumption of uniform…

Statistics Theory · Mathematics 2023-06-13 Anass Aghbalou , François Portier , Anne Sabourin

We consider the model selection consistency or sparsistency of a broad set of $\ell_1$-regularized $M$-estimators for linear and non-linear statistical models in a unified fashion. For this purpose, we propose the local structured…

Statistics Theory · Mathematics 2014-10-29 Yen-Huan Li , Jonathan Scarlett , Pradeep Ravikumar , Volkan Cevher

For a large class of regularized models, leave-one-out cross-validation can be efficiently estimated with an approximate leave-one-out formula (ALO). We consider the problem of adjusting hyperparameters so as to optimize ALO. We derive…

Machine Learning · Statistics 2020-11-23 Ryan Burn

We give a concentration inequality based on the premise that random variables take values within a particular region. The concentration inequality guarantees that, for any sequence of correlated random variables, the difference between the…

Probability · Mathematics 2020-02-21 Go Kato

Leave-one-out cross-validation (LOOCV) can be particularly accurate among cross-validation (CV) variants for machine learning assessment tasks -- e.g., assessing methods' error or variability. But it is expensive to re-fit a model $N$ times…

Machine Learning · Statistics 2020-06-24 William T. Stephenson , Tamara Broderick

The singular subspaces perturbation theory is of fundamental importance in probability and statistics. It has various applications across different fields. We consider two arbitrary matrices where one is a leave-one-column-out submatrix of…

Statistics Theory · Mathematics 2024-01-17 Anderson Y. Zhang , Harrison H. Zhou

It is well known that if the power spectral density of a continuous time stationary stochastic process does not have a compact support, data sampled from that process at any uniform sampling rate leads to biased and inconsistent spectrum…

Statistics Theory · Mathematics 2010-06-09 Radhendushka Srivastava , Debasis Sengupta