Metraipolis › archive › dc_53839929aed3

The Geometry of Anisotropic Dilation for Optimal Regularization — arXiv:2610.09310

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09310
License (as archived)
CC0-1.0
Archived
2026-10-08T12:39:58.717Z
SHA-256 of the archived text
c1fc3fa792ead960861823bb8f2ef50bbd00a4cccbb43f08309f9a2dcb3c8474
Stable URL of this page
https://metraipolis.com/documento/dc_53839929aed3

How to cite

The Geometry of Anisotropic Dilation for Optimal Regularization — arXiv:2610.09310 — arXiv (en), https://arxiv.org/abs/2610.09310 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53839929aed3 (Metraipolis archive dc_53839929aed3, sha256 c1fc3fa792ead960861823bb8f2ef50bbd00a4cccbb43f08309f9a2dcb3c8474)
BibTeX
@misc{dc53839929aed3,
  title = {The Geometry of Anisotropic Dilation for Optimal Regularization — arXiv:2610.09310},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09310},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53839929aed3; sha256 c1fc3fa792ead960861823bb8f2ef50bbd00a4cccbb43f08309f9a2dcb3c8474},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09310. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A central question in data-driven inverse problems is how to construct a regularizer that adapts to the geometry of the data distribution. Recent work in optimal regularization shows that, within a broad Gibbs class, the regularizer best matched to a distribution $P$ is determined by a single, direction-dependent radial summary statistic $\rho_P$. This suggests a way to control regularizer geometry by transforming the data. In particular, which transformations act on $\rho_P$ in a simple, explicit way? Can they improve the optimization properties of the resulting variational problems or adapt a fixed base regularizer to data? To address these questions, we introduce anisotropic dilation, a direction-preserving map that rescales each point along its Euclidean ray by a positive profile on the sphere. Despite its simplicity, this family acts transitively on the space of radial summary statistics: any target regularizer in the Gibbs class can be reached from any source distribution by a single explicit profile. We characterize the resulting orbit structure on distributions, derive in closed form the profile that optimally adapts a fixed base regularizer to the data, and show that its improvement over isotropic rescaling is governed by a Jensen gap that is provably positive for several natural families. We also establish finite-sample generalization bounds for jointly learning the base regularizer and anisotropic profile, with explicit rates when the logarithm of the profile is parameterized by linear feature models or sparse ReLU networks. Building on this theory, we parameterize the base regularizer and anisotropic profile and learn them jointly from samples, yielding a data-adaptive regularizer for variational inverse problems. Experiments on a controlled two-dimensional family and MNIST denoising show that learning the profile further improves performance.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Metric Geometry (math.MG); Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.09310 — 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 2026-10-08T12:15:00.345Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).