Oracle inequalities for square root analysis estimators with application to total variation penalties
Information and Inference: A Journal of the IMA · 2021
DOI: 10.1093/imaiai/iaaa002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information and Inference: A Journal of the IMA, 2021. Verfasst von Francesco Ortelli und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben.
Abstract (Originalsprache)
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 et al. (2017, Bernoulli, 23, 552–581). 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.
Zitieren
APA
Ortelli, F., & Geer, S. V. D. (2021). Oracle inequalities for square root analysis estimators with application to total variation penalties. Information and Inference: A Journal of the IMA. https://doi.org/10.1093/imaiai/iaaa002
Vancouver
Ortelli F, Geer SVD. Oracle inequalities for square root analysis estimators with application to total variation penalties. Information and Inference: A Journal of the IMA. 2021. doi:10.1093/imaiai/iaaa002
BibTeX
@article{Ortelli2021,
author = {Ortelli, Francesco and Geer, Sara van de},
title = {Oracle inequalities for square root analysis estimators with application to total variation penalties},
journal = {Information and Inference: A Journal of the IMA},
year = {2021},
doi = {10.1093/imaiai/iaaa002}
}
EUVIMED