paper-with-me

Papers

From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators

2026-03-20 · Karun Adusumilli, Maximilian Kasy, Ashia Wilson arxiv

We derive the asymptotic risk function of regularized empirical risk minimization (ERM) estimators tuned by $n$-fold cross-validation (CV). The out-of-sample prediction loss of such estimators converges in distribution to the squared-error loss (risk function) of shrinkage estimators in the normal means model, tuned by Stein's unbiased risk estimate (SURE). This risk function provides a more fine-grained picture of predictive performance than uniform bounds on worst-case regret, which are common in learning theory: it quantifies how risk varies with the true parameter. As key intermediate steps, we show that (i) $n$-fold CV converges uniformly to SURE, and (ii) while SURE typically has multiple local minima, its global minimum is generically well separated. Well-separation ensures that uniform convergence of CV to SURE translates into convergence of the tuning parameter chosen by CV to that chosen by SURE.

📄 PDF Abstract BibTeX arXiv:2603.20388

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mitigating optimistic bias in entropic risk estimation and optimization with an application to insurance

2024-09-30 · Utsav Sadana, Erick Delage, Angelos Georghiou

The entropic risk measure is widely used in high-stakes decision making to account for tail risks associated with an uncertain loss. With limited data, the empirical entropic risk estimator, i.e. replacing the expectatio…

Decision MakingDecision Making Under Uncertainty

Asymptotically free sketched ridge ensembles: Risks, cross-validation, and tuning

2023-10-06 · Pratik Patil, Daniel LeJeune

We employ random matrix theory to establish consistency of generalized cross validation (GCV) for estimating prediction risks of sketched ridge regression ensembles, enabling efficient and consistent tuning of regulariza…

PredictionPrediction Intervalsregression

Cross-Audit Projection for Model Risk Prediction

2026-07-02 · Yijian Huang arxiv

For training-data-based model risk prediction, $K$-fold cross-validation~(CV) is widely used to mitigate the well-known over-optimism of the empirical risk and is often regarded as reliable. However, for binary classific…

Breast Cancer DetectionBinary Classification

Mitigating multiple descents: A model-agnostic framework for risk monotonization

2022-05-25 · Pratik Patil, Arun Kumar Kuchibhotla, Yuting Wei, Alessandro Rinaldo

Recent empirical and theoretical analyses of several commonly used prediction procedures reveal a peculiar risk behavior in high dimensions, referred to as double/multiple descent, in which the asymptotic risk is a non-m…

Prediction

Risk and cross validation in ridge regression with correlated samples

2024-08-08 · Alexander Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan

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 theo…

regressionTime SeriesTime Series Forecasting