Metraipolis › archive › dc_560b3cf7d548
Symmetry-quotient Flatness and Generalization — arXiv:2609.31634
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31634
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:36:01.085Z
- SHA-256 of the archived text
359d107fe0125825c9e669f23d939c5b0c9c8aa0c8bd66143d9a0763cbb2437a- Stable URL of this page
https://metraipolis.com/documento/dc_560b3cf7d548
How to cite
Symmetry-quotient Flatness and Generalization — arXiv:2609.31634 — arXiv (en), https://arxiv.org/abs/2609.31634 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_560b3cf7d548 (Metraipolis archive dc_560b3cf7d548, sha256 359d107fe0125825c9e669f23d939c5b0c9c8aa0c8bd66143d9a0763cbb2437a)
BibTeX
@misc{dc560b3cf7d548,
title = {Symmetry-quotient Flatness and Generalization — arXiv:2609.31634},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31634},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_560b3cf7d548; sha256 359d107fe0125825c9e669f23d939c5b0c9c8aa0c8bd66143d9a0763cbb2437a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31634. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper develops a theorem-level pipeline in symmetry-quotient settings: quotient linear stability implies quotient flatness, quotient flatness implies input smoothness, and input smoothness yields generalization under local covering assumptions. Flatness is often associated with generalization, and Stochastic Gradient Descent (SGD) is frequently viewed as implicitly biased toward flat solutions. However, standard flatness measures are typically defined in the raw parameter space and are therefore not invariant under function-preserving symmetries such as positive rescaling. We develop a symmetry-aware theory of quotient flatness, quotient linear stability, input smoothness, and generalization on quotient spaces of neural-network parameters. For square loss and models equipped with function-preserving group actions, we define quotient flatness as the trace of the Hessian of the empirical loss on the regular quotient manifold. We show that quotient flatness controls input smoothness through a quotient-space analogue of the flatness-to-smoothness argument. We also prove that one-step mean-square quotient linear stability of the linearized SGD dynamics implies an explicit quotient-flatness bound in terms of the batch size and learning rate, and extend this analysis to higher-order tensor moments. Finally, under local covering and boundedness assumptions, we derive population generalization bounds in terms of quotient flatness and, consequently, in terms of quotient linear stability. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.31634 — 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 2026-10-07T22:14:27.513Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).