A minimaxity criterion in nonparametric regression based on large-deviations probabilities

DOI10.1214/aos/1032526957zbMath0862.62036OpenAlexW2025044155MaRDI QIDQ1816973

Alexander Korostelev

Publication date: 4 June 1997

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1032526957

zbMATH Keywords

Gaussian noiseminimax riskLipschitz classesexact asymptoticsHoelder classesoptimality of nonparametric regression estimators

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Large deviations (60F10)

Related Items (5)

Uniform \(L_1\)-distance large deviations in nonparametric density estimation ⋮ Large deviations theorems in nonparametric regression on functional data ⋮ Remarks on extremal problems in nonparametric curve estimation ⋮ Exact asymptotics for estimating the marginal density of discretely observed diffusion proc\-esses ⋮ Large deviations for the \(L_1\)-distance in kernel density estimation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimax Bahadur efficiency for small confidence levels.
• Large sample point estimation: A large deviation theory approach
• Estimates of location: a large deviation comparison
• Asymptotic minimax risk for sup-norm loss: Solution via optimal recovery
• Optimal global rates of convergence for nonparametric regression

This page was built for publication: A minimaxity criterion in nonparametric regression based on large-deviations probabilities