Towards the study of least squares estimators with convex penalty
From MaRDI portal
Publication:4557508
zbMATH Open1409.62133arXiv1701.09120MaRDI QIDQ4557508FDOQ4557508
Alexandre B. Tsybakov, Guillaume Lecué, Pierre C. Bellec
Publication date: 23 November 2018
Abstract: Penalized least squares estimation is a popular technique in high-dimensional statistics. It includes such methods as the LASSO, the group LASSO, and the nuclear norm penalized least squares. The existing theory of these methods is not fully satisfying since it allows one to prove oracle inequalities with fixed high probability only for the estimators depending on this probability. Furthermore, the control of compatibility factors appearing in the oracle bounds is often not explicit. Some very recent developments suggest that the theory of oracle inequalities can be revised in an improved way. In this paper, we provide an overview of ideas and tools leading to such an improved theory. We show that, along with overcoming the disadvantages mentioned above, the methodology extends to the hilbertian framework and it applies to a large class of convex penalties. This paper is partly expository. In particular, we provide adapted proofs of some results from other recent work.
Full work available at URL: https://arxiv.org/abs/1701.09120
Cited In (5)
- Title not available (Why is that?)
- Concentration behavior of the penalized least squares estimator
- Penalized least square in sparse setting with convex penalty and non Gaussian errors
- Discussion of ``On concentration for (regularized) empirical risk minimization by Sara van de Geer and Martin Wainwright
- On the risk of convex-constrained least squares estimators under misspecification
This page was built for publication: Towards the study of least squares estimators with convex penalty
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4557508)
