Salvato in:
Dettagli Bibliografici
Autori principali: Furuhashi, Takanobu, Hontani, Hidekata, Zhao, Qibin, Yokota, Tatsuya
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.20447
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918296139333632
author Furuhashi, Takanobu
Hontani, Hidekata
Zhao, Qibin
Yokota, Tatsuya
author_facet Furuhashi, Takanobu
Hontani, Hidekata
Zhao, Qibin
Yokota, Tatsuya
contents Sparse regularization is fundamental in signal processing and feature extraction but often relies on non-differentiable penalties, conflicting with gradient-based optimizers. We propose WEEP (Weakly-convex Envelope of Piecewise Penalty), a novel differentiable regularizer derived from the weakly-convex envelope framework. WEEP provides tunable, unbiased sparsity and a simple closed-form proximal operator, while maintaining full differentiability and L-smoothness, ensuring compatibility with both gradient-based and proximal algorithms. This resolves the tradeoff between statistical performance and computational tractability. We demonstrate superior performance compared to established convex and non-convex sparse regularizers on challenging compressive sensing and image denoising tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20447
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WEEP: A Differentiable Nonconvex Sparse Regularizer via Weakly-Convex Envelope
Furuhashi, Takanobu
Hontani, Hidekata
Zhao, Qibin
Yokota, Tatsuya
Machine Learning
Computer Vision and Pattern Recognition
Sparse regularization is fundamental in signal processing and feature extraction but often relies on non-differentiable penalties, conflicting with gradient-based optimizers. We propose WEEP (Weakly-convex Envelope of Piecewise Penalty), a novel differentiable regularizer derived from the weakly-convex envelope framework. WEEP provides tunable, unbiased sparsity and a simple closed-form proximal operator, while maintaining full differentiability and L-smoothness, ensuring compatibility with both gradient-based and proximal algorithms. This resolves the tradeoff between statistical performance and computational tractability. We demonstrate superior performance compared to established convex and non-convex sparse regularizers on challenging compressive sensing and image denoising tasks.
title WEEP: A Differentiable Nonconvex Sparse Regularizer via Weakly-Convex Envelope
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.20447