Exponential weighting and oracle inequalities for projection estimates
From MaRDI portal
(Redirected from Publication:1928229)
Abstract: We consider the problem of recovering an unknown vector from noisy data with the help of projection estimates. The goal is to find a convex combination of these estimates with the minimal risk. We study an aggregation method based on the so-called exponential weighting and provide a new upper bound for the mean square risk of this method.
Recommendations
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
- ON BOUNDS AND APPROXIMATING WEIGHTED DISTRIBUTIONS BY EXPONENTIAL DISTRIBUTIONS
- Oracle inequalities for probability density estimations
- On the weighted exponential approximations
- Concentration inequalities for the exponential weighting method
- Exponential inequalities and estimation of conditional probabilities
- Extrapolation of weights revisited: new proofs and sharp bounds
- scientific article; zbMATH DE number 17207
- Exponential inequalities in stochastic approximation procedures
- Oracle inequalities and nonparametric function estimation
Cites work
Cited in
(6)- On a method of empirical risk minimization
- Optimal exponents in weighted estimates without examples
- Ordered smoothers with exponential weighting
- Adaptivity and oracle inequalities in linear statistical inverse problems: a (numerical) survey
- Concentration inequalities for the exponential weighting method
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
This page was built for publication: Exponential weighting and oracle inequalities for projection estimates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1928229)