Uniform consistency of cross-validation estimators for high-dimensional ridge regression
We examine generalized and leave-one-out cross-validation for ridge regression in a
proportional asymptotic framework where the dimension of the feature space grows …
proportional asymptotic framework where the dimension of the feature space grows …
On the interplay between noise and curvature and its effect on optimization and generalization
The speed at which one can minimize an expected loss using stochastic methods depends
on two properties: the curvature of the loss and the variance of the gradients. While most …
on two properties: the curvature of the loss and the variance of the gradients. While most …
Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent
We analyze the statistical properties of generalized cross-validation (GCV) and leave-one-
out cross-validation (LOOCV) applied to early-stopped gradient descent (GD) in high …
out cross-validation (LOOCV) applied to early-stopped gradient descent (GD) in high …
Hypothesis transfer learning with surrogate classification losses: Generalization bounds through algorithmic stability
Hypothesis transfer learning (HTL) contrasts domain adaptation by allowing for a previous
task leverage, named the source, into a new one, the target, without requiring access to the …
task leverage, named the source, into a new one, the target, without requiring access to the …
Leave-one-out cross-validation for Bayesian model comparison in large data
Recently, new methods for model assessment, based on subsampling and posterior
approximations, have been proposed for scaling leave-one-out cross-validation (LOO-CV) to …
approximations, have been proposed for scaling leave-one-out cross-validation (LOO-CV) to …
Asymptotics of cross-validation
Cross validation is a central tool in evaluating the performance of machine learning and
statistical models. However, despite its ubiquitous role, its theoretical properties are still not …
statistical models. However, despite its ubiquitous role, its theoretical properties are still not …
Subsample ridge ensembles: Equivalences and generalized cross-validation
We study subsampling-based ridge ensembles in the proportional asymptotics regime,
where the feature size grows proportionally with the sample size such that their ratio …
where the feature size grows proportionally with the sample size such that their ratio …
Iterative approximate cross-validation
Cross-validation (CV) is one of the most popular tools for assessing and selecting predictive
models. However, standard CV suffers from high computational cost when the number of …
models. However, standard CV suffers from high computational cost when the number of …
Approximate cross-validation: Guarantees for model assessment and selection
Cross-validation (CV) is a popular approach for assessing and selecting predictive models.
However, when the number of folds is large, CV suffers from a need to repeatedly refit a …
However, when the number of folds is large, CV suffers from a need to repeatedly refit a …
Is Cross-Validation the Gold Standard to Evaluate Model Performance?
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 …
learning models. Despite its wide usage, their statistical benefits have remained half …