Metraipolis › archive › dc_5deef1191489
General Frequency Principle for Linear Approximation Classes — arXiv:2610.41179
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41179
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:40:42.978Z
- SHA-256 of the archived text
0e3f7618ed5e7ed04018d84e6293897279fbeee3c67cab29e5971e077f33d10d- Stable URL of this page
https://metraipolis.com/documento/dc_5deef1191489
How to cite
General Frequency Principle for Linear Approximation Classes — arXiv:2610.41179 — arXiv (en), https://arxiv.org/abs/2610.41179 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5deef1191489 (Metraipolis archive dc_5deef1191489, sha256 0e3f7618ed5e7ed04018d84e6293897279fbeee3c67cab29e5971e077f33d10d)
BibTeX
@misc{dc5deef1191489,
title = {General Frequency Principle for Linear Approximation Classes — arXiv:2610.41179},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41179},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5deef1191489; sha256 0e3f7618ed5e7ed04018d84e6293897279fbeee3c67cab29e5971e077f33d10d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41179. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we study a general frequency principle under gradient descent training for the finite linear approximation classes. Under suitable assumptions, we prove that the learner amplitude relative to the target amplitude vanishes at high frequencies, uniformly throughout training. We also establish sufficient conditions for low-frequency priority, covering single-frequency targets trained separately and two frequency components trained in the same run. This general frequency principle does not imply that lower frequencies always converge faster. Instead, for two frequencies that satisfy certain comparison conditions, one component will take longer to learn than the other; and in common cases, the longer component has higher frequency. Numerical experiments with Legendre and trigonometric bases validate the theoretical results. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA). Pagina del lavoro: https://arxiv.org/abs/2610.41179 — 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 2026-11-03T05:26:25.669Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).