FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION

DOI10.1017/S0266466608080225zbMath1284.62583OpenAlexW2083853335WikidataQ105583873 ScholiaQ105583873MaRDI QIDQ3632389

Bartlett, Peter L.

Publication date: 11 June 2009

Published in: Econometric Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1017/s0266466608080225

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20)

Related Items (5)

On least squares estimation under heteroscedastic and heavy-tailed errors ⋮ Deep learning: a statistical viewpoint ⋮ Regularization in kernel learning ⋮ \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities ⋮ Performance guarantees for individualized treatment rules

Cites Work

• A decision-theoretic generalization of on-line learning and an application to boosting
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Empirical minimization
• Local Rademacher complexities
• Improving the sample complexity using global data
• 10.1162/1532443041424319
• Asymptotic distribution of the errors in scalar and vector quantizers
• Convexity, Classification, and Risk Bounds
• Some applications of concentration inequalities to statistics
• Model selection and error estimation

This page was built for publication: FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION