paper-with-me

Papers

Oracle inequalities for square root analysis estimators with application to total variation penalties

2019-02-28 · Francesco Ortelli, Sara van de Geer

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.

📄 PDF Abstract BibTeX arXiv:1902.11192

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Oracle Inequalities for High-dimensional Prediction

2016-08-01 · Johannes Lederer, Lu Yu, Irina Gaynanova

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 Prediction

Aggregation of Affine Estimators

2013-11-12 · Dong Dai, Philippe Rigollet, Lucy Xia, Tong Zhang

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 Selection

Mallows-type model averaging: Non-asymptotic analysis and all-subset combination

2025-05-05 · Jingfu Peng

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 Selection

Heterogeneous Overdispersed Count Data Regressions via Double Penalized Estimations

2021-10-07 · Shaomin Li, Haoyu Wei, Xiaoyu Lei

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…

regression

Outlier-robust sparse/low-rank least-squares regression and robust matrix completion

2020-12-12 · Philip Thompson

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