Support Localization and the Fisher Metric for off-the-grid Sparse Regularization
Lists
Only you see this
Abstract
Sparse regularization is a central technique for both machine learning (to achieve supervised features selection or unsupervised mixture learning) and imaging sciences (to achieve super-resolution). Existing performance guaranties assume a separation of the spikes based on an ad-hoc (usually Euclidean) minimum distance condition, which ignores the geometry of the problem. In this article, we study the BLASSO (i.e. the off-the-grid version of $\ell^1$ LASSO regularization) and show that the Fisher-Rao distance is the natural way to ensure and quantify support recovery, since it preserves the invariance of the problem under reparameterization. We prove that under mild regularity and curvature conditions, stable support identification is achieved even in the presence of randomized sub-sampled observations (which is the case in compressed sensing or learning scenario). On deconvolution problems, which are translation invariant, this generalizes to the multi-dimensional setting existing results of the literature. For more complex translation-varying problems, such as Laplace transform inversion, this gives the first geometry-aware guarantees for sparse recovery.
BibTeX
@inproceedings{poon2019support,
author = {Clarice Poon and Nicolas Keriven and Gabriel Peyré},
title = {{Support Localization and the Fisher Metric for off-the-grid Sparse Regularization}},
booktitle = {International Conference on Artificial Intelligence and Statistics},
year = {2019},
url = {https://openreview.net/forum?id=oeUjuPEzvpS},
}| A Dual Certificates Analysis of Compressive Off-the-Grid Recovery | arXiv · 2018 |
| Support Recovery for Sparse Deconvolution of Positive Measures | arXiv · 2015 |
| Spike detection from inaccurate samplings | Applied and Computational Harmonic Analysis · 2014 |
| The basins of attraction of the global minimizers of non-convex inverse problems with low-dimensional models in infinite dimension | arXiv · 2020 |
| MultiDimensional Sparse Super-Resolution | arXiv · 2017 |
| Sparse Spikes Deconvolution on Thin Grids | arXiv · 2015 |