Concentration inequalities for the exponential weighting method
From MaRDI portal
Publication:461822
DOI10.3103/S1066530714010025zbMath1310.62012OpenAlexW2095579730MaRDI QIDQ461822
J. Herrera, D. Rodríguez-Gómez
Publication date: 15 October 2014
Published in: Mathematical Methods of Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.3103/s1066530714010025
concentration inequalityoracle inequalityexponential weightingordered smoothersunbiased risk estimation
Linear regression; mixed models (62J05) Inequalities; stochastic orderings (60E15) Bayesian problems; characterization of Bayes procedures (62C10) Minimax procedures in statistical decision theory (62C20)
Related Items
On risk concentration for convex combinations of linear estimators, An oracle inequality for quasi-Bayesian nonnegative matrix factorization, Tikhonov-Phillips regularizations in linear models with blurred design, Indefinite integrals of generalized intuitionistic multiplicative functions, On the exponentially weighted aggregate with the Laplace prior
Cites Work
- Unnamed Item
- Unnamed Item
- Ordered smoothers with exponential weighting
- On universal oracle inequalities related to high-dimensional linear models
- Linear and convex aggregation of density estimators
- Oscillation matrices with spline smoothing
- Ordered linear smoothers
- Combining different procedures for adaptive regression
- Functional aggregation for nonparametric regression.
- Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
- Exponential weighting and oracle inequalities for projection estimates
- Sharp oracle inequalities for aggregation of affine estimators
- PAC-Bayesian bounds for sparse regression estimation with exponential weights
- Estimation and variable selection with exponential weights
- Simultaneous adaptation to the margin and to complexity in classification
- Information Theory and Mixing Least-Squares Regressions
- Some Comments on C P
- Sparse estimation by exponential weighting