On universal oracle inequalities related to high-dimensional linear models
From MaRDI portal
Publication:605926
DOI10.1214/10-AOS803zbMath1200.62074arXiv1011.2378MaRDI QIDQ605926
Publication date: 15 November 2010
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1011.2378
oracle inequality; empirical risk minimization; ordered smoother; excess risk; spectral regularization
62H99: Multivariate analysis
62J05: Linear regression; mixed models
60E15: Inequalities; stochastic orderings
62G05: Nonparametric estimation
62C10: Bayesian problems; characterization of Bayes procedures
15A18: Eigenvalues, singular values, and eigenvectors
Related Items
Adaptivity and Oracle Inequalities in Linear Statistical Inverse Problems: A (Numerical) Survey, Solution of linear ill-posed problems using overcomplete dictionaries, Ordered smoothers with exponential weighting, Concentration inequalities for the exponential weighting method, Noisy Laplace deconvolution with error in the operator, Tikhonov-Phillips regularizations in linear models with blurred design, Sharp oracle inequalities for aggregation of affine estimators, Adaptive spectral regularizations of high dimensional linear models, Empirical risk minimization as parameter choice rule for general linear regularization methods, Spectral cut-off regularizations for ill-posed linear models, On risk concentration for convex combinations of linear estimators, Spatially inhomogeneous linear inverse problems with possible singularities
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Risk hull method and regularization by projections of ill-posed inverse problems
- A statistical perspective on ill-posed inverse problems (with discussion)
- The principle of penalized empirical risk in severely ill-posed problems
- Optimal filtering of square-integrable signals in Gaussian noise
- Ordered linear smoothers
- Weak convergence and empirical processes. With applications to statistics
- Adaptive complexity regularization for linear inverse problems
- A Lepskij-type stopping rule for regularized Newton methods
- Statistical Inverse Estimation in Hilbert Scales
- Convergence Rates of General Regularization Methods for Statistical Inverse Problems and Applications
- The Lepskii principle revisited
- An Iteration Formula for Fredholm Integral Equations of the First Kind