HIGH-DIMENSIONAL ASYMPTOTICS OF PREDICTION: RIDGE REGRESSION AND CLASSIFICATION

• 成果类型: Article
• 署名作者: Dobriban, Edgar; Wager, Stefan
• 署名单位: University of Pennsylvania; Stanford University
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/17-AOS1549
• 发表日期: 2018
• 页码: 247-279
• 关键词: convergence; eigenvalues; expansion; estimator; RISK

摘要

We provide a unified analysis of the predictive risk of ridge regression and regularized discriminant analysis in a dense random effects model. We work in a high-dimensional asymptotic regime where p, n -> infinity and p/n -> gamma > 0, and allow for arbitrary covariance among the features. For both methods, we provide an explicit and efficiently computable expression for the limiting predictive risk, which depends only on the spectrum of the feature-covariance matrix, the signal strength and the aspect ratio.. Especially in the case of regularized discriminant analysis, we find that predictive accuracy has a nuanced dependence on the eigenvalue distribution of the covariance matrix, suggesting that analyses based on the operator norm of the covariance matrix may not be sharp. Our results also uncover an exact inverse relation between the limiting predictive risk and the limiting estimation risk in high-dimensional linear models. The analysis builds on recent advances in random matrix theory.