Metraipolis › archive › dc_a5de853da4ea
Efficient Learning and Symmetry Discovery under Exact Invariances — arXiv:2609.07031
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07031
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:57:37.744Z
- SHA-256 of the archived text
5ad672b8f387a3da6861eb391f38ee41b9cba570d4d5d440c47275f5cb20a386- Stable URL of this page
https://metraipolis.com/documento/dc_a5de853da4ea
How to cite
Efficient Learning and Symmetry Discovery under Exact Invariances — arXiv:2609.07031 — arXiv (en), https://arxiv.org/abs/2609.07031 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5de853da4ea (Metraipolis archive dc_a5de853da4ea, sha256 5ad672b8f387a3da6861eb391f38ee41b9cba570d4d5d440c47275f5cb20a386)
BibTeX
@misc{dca5de853da4ea,
title = {Efficient Learning and Symmetry Discovery under Exact Invariances — arXiv:2609.07031},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07031},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5de853da4ea; sha256 5ad672b8f387a3da6861eb391f38ee41b9cba570d4d5d440c47275f5cb20a386},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07031. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning with group invariances is central to many scientific and geometric learning problems, yet its computational foundations remain poorly understood. Even for classical supervised regression settings, it has been unclear whether one can efficiently compute a regression function that is exactly invariant to a given group action. Recent work showed that exact invariance can be enforced in polynomial time when the underlying group is finite and known, but left open the cases of infinite groups and unknown symmetries. In this paper, we resolve both challenges. First, we present the first polynomial-time algorithm for learning with exact group invariances that applies uniformly to finite and infinite groups. The runtime is polynomial in the data dimension and sample size, and independent of the group, while achieving strong generalization guarantees. This provides a computational explanation for the empirical success of invariant and equivariant methods in geometric machine learning and partially answers a recent open question in the literature. Second, we study learning in the symmetry discovery setting, where the invariance group is unknown. Focusing on the subgroup lattice of a finite group, we show that exact symmetries can be identified from data and exploited for learning in polynomial time. For regression over finite-dimensional feature spaces, our algorithm provably recovers the underlying symmetry, matches the minimax-optimal sample complexity of the known-symmetry setting, and runs in time polynomial in the data dimension and sample size. Our analysis relies on tools from random Cayley graphs and expander theory, which may be of independent interest. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.07031 — 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 2026-10-16T13:39:42.930Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).