Adaptive Recovery of Signals by Convex Optimization
Abstract
We present a theoretical framework for adaptive estimation and prediction of signals of unknown structure in the presence of noise. The framework allows to address two intertwined challenges: (i) designing optimal statistical estimators; (ii) designing efficient numerical algorithms. In particular, we establish oracle inequalities for the performance of adaptive procedures, which rely upon convex optimization and thus can be efficiently implemented. As an application of the proposed approach, we consider denoising of harmonic oscillations.
Cite
Text
Harchaoui et al. "Adaptive Recovery of Signals by Convex Optimization." Annual Conference on Computational Learning Theory, 2015.Markdown
[Harchaoui et al. "Adaptive Recovery of Signals by Convex Optimization." Annual Conference on Computational Learning Theory, 2015.](https://mlanthology.org/colt/2015/harchaoui2015colt-adaptive/)BibTeX
@inproceedings{harchaoui2015colt-adaptive,
title = {{Adaptive Recovery of Signals by Convex Optimization}},
author = {Harchaoui, Zaïd and Juditsky, Anatoli B. and Nemirovski, Arkadi and Ostrovsky, Dmitry},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2015},
pages = {929-955},
url = {https://mlanthology.org/colt/2015/harchaoui2015colt-adaptive/}
}