中文
相关论文

相关论文: Failures and Successes of Cross-Validation for Ear…

200 篇论文

Evaluating the predictive performance of a statistical model is commonly done using cross-validation. Among the various methods, leave-one-out cross-validation (LOOCV) is frequently used. Originally designed for exchangeable observations,…

统计计算 · 统计学 2025-07-04 Zhedong Liu , Janet Van Niekerk , Haavard Rue

Generalized cross-validation (GCV) is a widely-used method for estimating the squared out-of-sample prediction risk that employs a scalar degrees of freedom adjustment (in a multiplicative sense) to the squared training error. In this…

统计理论 · 数学 2024-04-23 Pierre C. Bellec , Jin-Hong Du , Takuya Koriyama , Pratik Patil , Kai Tan

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…

机器学习 · 统计学 2020-06-24 William T. Stephenson , Tamara Broderick

Standard techniques such as leave-one-out cross-validation (LOOCV) might not be suitable for evaluating the predictive performance of models incorporating structured random effects. In such cases, the correlation between the training and…

统计方法学 · 统计学 2024-06-21 A. Adin , E. Krainski , A. Lenzi , Z. Liu , J. Martínez-Minaya , H. Rue

We describe a fast computation method for leave-one-out cross-validation (LOOCV) for $k$-nearest neighbours ($k$-NN) regression. We show that, under a tie-breaking condition for nearest neighbours, the LOOCV estimate of the mean square…

机器学习 · 统计学 2024-12-05 Motonobu Kanagawa

Recent years have seen substantial advances in our understanding of high-dimensional ridge regression, but existing theories assume that training examples are independent. By leveraging techniques from random matrix theory and free…

机器学习 · 统计学 2025-11-06 Alexander Atanasov , Jacob A. Zavatone-Veth , Cengiz Pehlevan

Cross-validation (CV) is a common method to tune machine learning methods and can be used for model selection in regression as well. Because of the structured nature of small, traditional experimental designs, the literature has warned…

应用统计 · 统计学 2025-06-18 Maria L. Weese , Byran J. Smucker , David J. Edwards

Two key tasks in high-dimensional regularized regression are tuning the regularization strength for accurate predictions and estimating the out-of-sample risk. It is known that the standard approach -- $k$-fold cross-validation -- is…

统计理论 · 数学 2025-10-24 Kevin Luo , Yufan Li , Pragya Sur

Risk estimation is at the core of many learning systems. The importance of this problem has motivated researchers to propose different schemes, such as cross validation, generalized cross validation, and Bootstrap. The theoretical…

统计理论 · 数学 2021-01-19 Ji Xu , Arian Maleki , Kamiar Rahnama Rad , Daniel Hsu

It is useful to estimate the expected predictive performance of models planned to be used for prediction. We focus on leave-one-out cross-validation (LOO-CV), which has become a popular method for estimating predictive performance of…

统计方法学 · 统计学 2025-10-29 Tuomas Sivula , Måns Magnusson , Asael Alonzo Matamoros , Aki Vehtari

Common cross-validation (CV) methods like k-fold cross-validation or Monte-Carlo cross-validation estimate the predictive performance of a learner by repeatedly training it on a large portion of the given data and testing on the remaining…

机器学习 · 计算机科学 2021-11-30 Felix Mohr , Jan N. van Rijn

This study examines generalized cross-validation for the tuning parameter selection for ridge regression in high-dimensional misspecified linear models. The set of candidates for the tuning parameter includes not only positive values but…

统计理论 · 数学 2026-01-21 Akira Shinkyu

Tuning parameter selection is of critical importance for kernel ridge regression. To this date, data driven tuning method for divide-and-conquer kernel ridge regression (d-KRR) has been lacking in the literature, which limits the…

机器学习 · 统计学 2019-02-20 Ganggang Xu , Zuofeng Shang , Guang Cheng

In overparameterized logistic regression, gradient descent (GD) iterates diverge in norm while converging in direction to the maximum $\ell_2$-margin solution -- a phenomenon known as the implicit bias of GD. This work investigates…

机器学习 · 计算机科学 2025-07-01 Jingfeng Wu , Peter Bartlett , Matus Telgarsky , Bin Yu

Cross-validation can be used to measure a model's predictive accuracy for the purpose of model comparison, averaging, or selection. Standard leave-one-out cross-validation (LOO-CV) requires that the observation model can be factorized into…

统计方法学 · 统计学 2021-06-21 Paul-Christian Bürkner , Jonah Gabry , Aki Vehtari

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…

统计理论 · 数学 2023-06-13 Anass Aghbalou , François Portier , Anne Sabourin

We consider the parametric learning problem, where the objective of the learner is determined by a parametric loss function. Employing empirical risk minimization with possibly regularization, the inferred parameter vector will be biased…

机器学习 · 统计学 2017-11-16 Ahmad Beirami , Meisam Razaviyayn , Shahin Shahrampour , Vahid Tarokh

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…

机器学习 · 统计学 2016-10-26 Yoshiyuki Kabashima , Tomoyuki Obuchi , Makoto Uemura

We present a novel method for tuning the regularization hyper-parameter, $\lambda$, of a ridge regression that is faster to compute than leave-one-out cross-validation (LOOCV) while yielding estimates of the regression parameters of equal,…

机器学习 · 统计学 2023-11-06 Shu Yu Tew , Mario Boley , Daniel F. Schmidt

Despite ongoing theoretical research on cross-validation (CV), many theoretical questions remain widely open. This motivates our investigation into how properties of algorithm-distribution pairs can affect the choice for the number of folds…

统计理论 · 数学 2026-01-09 Ido Nachum , Rüdiger Urbanke , Thomas Weinberger
‹ 上一页 1 2 3 10 下一页 ›