Sharp Oracle Inequalities for High-Dimensional Matrix Prediction

DOI10.1109/TIT.2011.2136318MaRDI QIDQ5272315zbMATH OpenOpenAlexFDO

Authors Stéphane Gaïffas, Guillaume Lecué

Publication date 12 July 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tit.2011.2136318

Mathematics Subject Classification ID

Matrix completion problems (15A83) Inequalities; stochastic orderings (60E15) Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Ridge regression; shrinkage estimators (Lasso) (62J07)

Recommendations

• Oracle inequalities for high-dimensional prediction
• Sharp oracle inequalities in low rank estimation
• On oracle inequalities related to high dimensional linear models
• On universal oracle inequalities related to high-dimensional linear models
• Matrix shrinkage of high-dimensional expectation vectors
• Sharp oracle inequalities for low-complexity priors
• Oracle inequalities for high dimensional vector autoregressions
• Scalable inference for high-dimensional precision matrix
• Oracle inequalities for the Lasso in the high-dimensional Aalen multiplicative intensity model
• Efficient Minimax Estimation of a Class of High-Dimensional Sparse Precision Matrices

Cited in

(7)

• On the exponentially weighted aggregate with the Laplace prior
• Rank penalized estimators for high-dimensional matrices
• Iteratively reweighted _1-penalized robust regression
• A non-convex algorithm framework based on DC programming and DCA for matrix completion
• Noisy low-rank matrix completion with general sampling distribution
• Adaptive shrinkage of singular values
• Regularization and the small-ball method. II: Complexity dependent error rates

This page was built for publication: Sharp Oracle Inequalities for High-Dimensional Matrix Prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5272315)