Metraipolis › archive › dc_663dcd8ef177

Scalar Smoothness Is One Point on a Besov Spectrum — arXiv:2611.02037

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02037
License (as archived)
CC0-1.0
Archived
2026-11-03T18:37:07.565Z
SHA-256 of the archived text
92e2725696210b04da3a1707316357966b94722247ea21972010b14ddfce1e25
Stable URL of this page
https://metraipolis.com/documento/dc_663dcd8ef177

How to cite

Scalar Smoothness Is One Point on a Besov Spectrum — arXiv:2611.02037 — arXiv (en), https://arxiv.org/abs/2611.02037 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_663dcd8ef177 (Metraipolis archive dc_663dcd8ef177, sha256 92e2725696210b04da3a1707316357966b94722247ea21972010b14ddfce1e25)
BibTeX
@misc{dc663dcd8ef177,
  title = {Scalar Smoothness Is One Point on a Besov Spectrum — arXiv:2611.02037},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02037},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_663dcd8ef177; sha256 92e2725696210b04da3a1707316357966b94722247ea21972010b14ddfce1e25},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02037. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Studies of neural network generalization and robustness often summarize smoothness with a single number, such as a Lipschitz constant or a Hessian curvature statistic. However, Lipschitz constants summarize global worst-case sensitivity and Hessian statistics summarize local curvature; neither captures how model responses vary with the size, direction, and location of perturbations encountered in real-world deployment. To measure smoothness under these perturbations, we introduce a finite-difference roughness spectrum that profiles model responses across these conditions. Our roughness spectrum generalizes scalar smoothness measures, bringing Lipschitz sensitivity and directional Hessian curvature into a common framework across perturbation scales. We connect this spectrum to classical Besov theory, which describes how a function's variation changes with scale. Our theoretical analysis also proves that a larger output shift can cause less task damage than a smaller one, and that local curvature alone can miss the blocks most vulnerable to finite perturbations. In image classification, Roughness Source Control (RSC) suppresses margin roughness along noise directions and improves noise robustness in a comparison of 80 checkpoints across four model--dataset combinations. In post-training quantization, we identify blocks that need higher precision by measuring task-loss increases from perturbations matched to the size and direction of each block's quantization error. Our mixed-precision allocation achieves lower perplexity than the Hessian-based HAWQ-V2 baseline under the same GPTQ weights and bit budgets in all 14 settings across seven held-out large language models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.02037 — 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 2026-11-03T18:12:54.537Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).