Metraipolis › archive › dc_2ff157fe0f01
DREAM: Deep-Reparametrization of Adaptive Regularization Maps for Fast Zero-Shot Self-Supervised Learning — arXiv:2609.04019
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04019
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:26:51.724Z
- SHA-256 of the archived text
a282b602ccf257c5cf8531bb667efe452d60a97d7ddf4d333e4a8678126579b7- Stable URL of this page
https://metraipolis.com/documento/dc_2ff157fe0f01
How to cite
DREAM: Deep-Reparametrization of Adaptive Regularization Maps for Fast Zero-Shot Self-Supervised Learning — arXiv:2609.04019 — arXiv (en), https://arxiv.org/abs/2609.04019 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ff157fe0f01 (Metraipolis archive dc_2ff157fe0f01, sha256 a282b602ccf257c5cf8531bb667efe452d60a97d7ddf4d333e4a8678126579b7)
BibTeX
@misc{dc2ff157fe0f01,
title = {DREAM: Deep-Reparametrization of Adaptive Regularization Maps for Fast Zero-Shot Self-Supervised Learning — arXiv:2609.04019},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04019},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ff157fe0f01; sha256 a282b602ccf257c5cf8531bb667efe452d60a97d7ddf4d333e4a8678126579b7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04019. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Adaptive regularization is an effective means of improving the flexibility of classical variational reconstruction methods while retaining their interpretability and mathematical structure. In this work, we propose an approach for learning deep-reparameterized adaptive regularization maps (DREAM) for Total Variation (TV) and Total Generalized Variation (TGV) through algorithm unrolling in a zero-shot, self-supervised setting, requiring no access to large paired datasets. We first validate DREAM on a two-dimensional image-denoising problem and then apply it to large-scale dynamic MRI reconstruction. The resulting adaptive models are theoretically grounded, as they retain the convergence properties of the primal-dual algorithm used as the building block of the unrolled architecture. Our results show that the regularization parameter maps can be learned efficiently, requiring substantially fewer weight updates than state-of-the-art methods to achieve comparable performance. We further demonstrate that the CNN parametrization of the maps acts as an implicit prior and provides effective dimensionality reduction, outperforming direct optimization of the adaptive parameters. Across both applications, the performance gap between supervised and zero-shot training is smaller for DREAM than for the end-to-end deep-learning methods considered for comparison. Remarkably, in dynamic cardiac MRI reconstruction, zero-shot training matches the performance of the supervised model. Moreover, the learned adaptive maps are highly interpretable, providing a compelling alternative to purely deep-learning-based methods when reference data are difficult to obtain. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-04 in math.OC). Categorie arXiv: Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.04019 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T02:07:43.347Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).