arXiv Machine Learning June 25, 2026 By Haoyu He, Hao Wang, Jiashan Wang, Qiankun Shi

The Effective Number of Nonzeros: Theory and Regularization for Sparse Recovery

Read the original on arXiv Machine Learning →

arXiv:2603. 13826v2 Announce Type: replace Abstract: Classical sparse recovery treats all nonzero entries equally, though numerical noise often creates long tails of negligible coefficients.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

efficiency

arXiv Machine Learning

Sep 10

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements

arXiv:2509.01809v2 Announce Type: replace-cross Abstract: We consider the problem of support recovery for sparse binary signals from noisy linear measurements. For sparse Gaussian measurement matrice...

By Youssef Chaabouni, David Gamarnik

efficiency

arXiv Computer Vision

Sep 22

Blind Deconvolution of Binary and Pattern Images with Pixel Intensity Constraints and Sparse Gradient Prior

arXiv:2609.23268v1 Announce Type: new Abstract: Blind image deconvolution (BID) is a prominent research topic in the field of imaging sciences, given its significant practical applications. Most exis...

By Qinghua Zhang, Xuesong Yang, Liangtian He, Liang-jian Deng, Jun Liu

efficiency

arXiv Machine Learning

Jul 9

Statistical inverse learning and $\ell^1$-regularization

arXiv:2607. 07468v1 Announce Type: cross Abstract: We study the recovery of sparse functions from finite, noisy, and indirect observations in the framework of statistical inverse learning.

By Abhishake Rastogi, Tatiana A. Bubba, Tapio Helin, Luca Ratti

efficiency

arXiv Machine Learning

Sep 10

Recovering linear images of sparse signals from indirect observations

arXiv:2609.06182v1 Announce Type: cross Abstract: In this paper, we develop and analyze techniques for recovering a linear image $Bx$ of an unknown signal $x$ from indirect noisy observation $\omega=...

By Anatoli Juditsky, Arkadi Nemirovski

arXiv Machine Learning

Jul 14

Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization

arXiv:2607. 10618v1 Announce Type: cross Abstract: We consider the recovery of a pair of sparse vectors from a limited number of nonlinear observations of their superposition: $y_i=g(\inner{\ba_i}{\bPhi\bw^\ast+\bPsi\bz^\ast})+e_i$, $i=1,\dots,m$, with $m\ll n$, incoherent orthonormal bases $\bPhi,\bPsi$, a scalar link $g$, and noise $e_i$ that may be heavy-tailed or contaminated.

By Raziyeh Takbiri

agents efficiency safety

arXiv Computer Vision

Sep 2

A Cone-Constrained Bilinear Decomposition for Total Scaled-Gradient Variation Models

arXiv:2609.00036v1 Announce Type: new Abstract: The total scaled-gradient variation (TSGV) regularizer, derived from sparse modeling of piecewise-linear structures, has been shown to preserve edges a...

By Haibin Su, Chunlin Wu, Huibin Chang, Zhifang Liu

One email a morning, machine-written

Related stories

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements

Blind Deconvolution of Binary and Pattern Images with Pixel Intensity Constraints and Sparse Gradient Prior

Statistical inverse learning and $\ell^1$-regularization

Recovering linear images of sparse signals from indirect observations

Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization

A Cone-Constrained Bilinear Decomposition for Total Scaled-Gradient Variation Models