Metraipolis › archive › dc_047dd4b999df
Langevin dynamics along the zero set of real-analytic potentials — arXiv:2608.09840
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09840
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:02:52.201Z
- SHA-256 of the archived text
6b2c6e6b61918a548ee3afd2d56b220beb34cf333d737d5542c70a258f502add- Stable URL of this page
https://metraipolis.com/documento/dc_047dd4b999df
How to cite
Langevin dynamics along the zero set of real-analytic potentials — arXiv:2608.09840 — arXiv (en), https://arxiv.org/abs/2608.09840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_047dd4b999df (Metraipolis archive dc_047dd4b999df, sha256 6b2c6e6b61918a548ee3afd2d56b220beb34cf333d737d5542c70a258f502add)
BibTeX
@misc{dc047dd4b999df,
title = {Langevin dynamics along the zero set of real-analytic potentials — arXiv:2608.09840},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09840},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_047dd4b999df; sha256 6b2c6e6b61918a548ee3afd2d56b220beb34cf333d737d5542c70a258f502add},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We consider the Langevin diffusion $dX_t = - \beta \nabla V(X_t) dt + \sqrt{2} dB_t$ for a general nonnegative real-analytic potential $V$ and a large parameter $\beta$. In the large-$\beta$ limit the process is confined to the zero set of $V$, assuming that it starts there. We derive a candidate limiting evolution on the zero set. To do so, the zero set is partitioned into strata according to a measure of local codimension known as the local learning coefficient and its multiplicity. It is then shown that the Dirichlet form associated with $X$ converges in a certain sense to a hierarchy of Dirichlet forms corresponding to a stochastic evolution on the strata. This evolution is strongly biased toward higher-dimensional, or "more singular", strata. This result is motivated by a question from Watanabe's singular learning theory regarding the learning dynamics of overparameterized statistical models and the generalization puzzle in deep learning. The result suggests a mechanism for the observation that stochastic gradient methods tend to be biased toward singular solutions that generalize well.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in stat.ML).
Categorie arXiv: Probability (math.PR) ; Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.09840 — 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 2026-10-19T09:01:32.163Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).