mlsanityData to 14 Oct 2026

Effective regions and kernels in continuous sparse regularisation, with application to sketched mixtures

arXiv 2507.08444 ↗First posted 11 Jul 2025math.ST stat.ML stat.THcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper advances the general theory of continuous sparse regularisation on measures with the Beurling-LASSO (BLASSO). This TV-regularised convex program on the space of measures allows to recover a sparse measure using a noisy observation from a measurement operator. While previous works have uncovered the central role played by this operator and its associated kernel in order to get estimation error bounds, the latter requires a technical local positive curvature (LPC) assumption to be verified on a case-by-case basis. In practice, this yields only few LPC-kernels for which this condition is proved. In this paper, we prove that the ``sinc-4'' kernel, used for signal recovery and mixture problems, does satisfy the LPC assumption. Furthermore, we introduce the kernel switch analysis, which allows to leverage on a known LPC-kernel as a pivot kernel to prove error bounds. Together, these results provide easy-to-check conditions to get error bounds for a large family of translation-invariant model kernels. Besides, we also show that known BLASSO guarantees can be made adaptive to the noise level. This improves on known results where this error is fixed with some parameters depending on the model kernel. We illustrate the interest of our results in the case of mixture model estimation, using band-limiting smoothing and sketching techniques to reduce the computational burden of BLASSO.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 44 references that are in the map. First posted on arXiv 11 Jul 2025.

Builds on

18 of 44 references.

References · 18

  1. 2016Variational Inference: A Review for Statisticianscited by 1,472
  2. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 364
  3. 2014Breaking the Curse of Dimensionality with Convex Neural Networkscited by 331
  4. 2019Sparse Optimization on Measures with Over-parameterized Gradient Descentcited by 50
  5. 2018On Representer Theorems and Convex Regularizationcited by 24
  6. 2013Exact Support Recovery for Sparse Spikes Deconvolutioncited by 22
  7. 2018The Sliding Frank-Wolfe Algorithm and its Application to Super-Resolution Microscopycited by 16
  8. 2015The Alternating Descent Conditional Gradient Method for Sparse Inverse Problemscited by 11
  9. 2017Compressive Statistical Learning with Random Feature Momentscited by 11
  10. 2020Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modelingcited by 8
  11. 2020Sketching Datasets for Large-Scale Learning (long version)cited by 6
  12. 2018Model Selection for Mixture Models - Perspectives and Strategiescited by 5
6 more
  1. 2016Adapting to unknown noise level in sparse deconvolutioncited by 4
  2. 2021Mathematical Theory of Computational Resolution Limit in Multi-dimensionscited by 3
  3. 2023FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measurescited by 3
  4. 2018Model-based Clusteringcited by 2
  5. 2023Revisiting RIP guarantees for sketching operators on mixture modelscited by 2
  6. 2024Second Maximum of a Gaussian Random Field and Exact (t-)Spacing testcited by 2

Built on by

Not cited yet.