Oracle inequalities for square root analysis estimators with application to total variation penalties
Through the direct study of the analysis estimator we derive oracle inequalities with fast and slow rates by adapting the arguments involving projections by Dalalyan, Hebiri and Lederer (2017). We then extend the theory to the square root analysis estimator. Finally, we focus on (square root) total variation regularized estimators on graphs and obtain constant-friendly rates, which, up to log-terms, match previous results obtained by entropy calculations. We also obtain an oracle inequality for the (square root) total variation regularized estimator over the cycle graph.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Oracle Inequalities for High-dimensional Prediction
The abundance of high-dimensional data in the modern sciences has generated tremendous interest in penalized estimators such as the lasso, scaled lasso, square-root lasso, elastic net, and many others. In this paper, we …
PredictionVocal Bursts Intensity PredictionAggregation of Affine Estimators
We consider the problem of aggregating a general collection of affine estimators for fixed design regression. Relevant examples include some commonly used statistical estimators such as least squares, ridge and robust le…
Model SelectionMallows-type model averaging: Non-asymptotic analysis and all-subset combination
Model averaging (MA) and ensembling play a crucial role in statistical and machine learning practice. When multiple candidate models are considered, MA techniques can be used to weight and combine them, often resulting i…
AllModel SelectionHeterogeneous Overdispersed Count Data Regressions via Double Penalized Estimations
This paper studies the non-asymptotic merits of the double $\ell_1$-regularized for heterogeneous overdispersed count data via negative binomial regressions. Under the restricted eigenvalue conditions, we prove the oracl…
regressionOutlier-robust sparse/low-rank least-squares regression and robust matrix completion
We study high-dimensional least-squares regression within a subgaussian statistical learning framework with heterogeneous noise. It includes $s$-sparse and $r$-low-rank least-squares regression when a fraction $\epsilon$…
Matrix Completionregressionvalid