Metraipolis › archive › dc_e59f2d287cf4

Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models — arXiv:2608.20183

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20183
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:27.495Z
SHA-256 of the archived text
bee09575edd977a6c469996b8eb6c772072e9795c0d157ca49bc82a3ea319a5d
Stable URL of this page
https://metraipolis.com/documento/dc_e59f2d287cf4

How to cite

Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models — arXiv:2608.20183 — arXiv (en), https://arxiv.org/abs/2608.20183 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e59f2d287cf4 (Metraipolis archive dc_e59f2d287cf4, sha256 bee09575edd977a6c469996b8eb6c772072e9795c0d157ca49bc82a3ea319a5d)
BibTeX
@misc{dce59f2d287cf4,
  title = {Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models — arXiv:2608.20183},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20183},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e59f2d287cf4; sha256 bee09575edd977a6c469996b8eb6c772072e9795c0d157ca49bc82a3ea319a5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20183. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect model selection in settings such as deep learning. The Widely Applicable Bayesian Information Criterion (WBIC) relies on local learning coefficients $\lambda$, which in the analytic case coincides with local Real Log Canonical Thresholds (RLCT) of the Kullback-Leibler divergence of the model, to capture correct marginal likelihood asymptotics. Exact computation of the learning coefficients has been limited to special cases, and only sampling-based estimation methods are generally applicable. We present the first deterministic algorithm that computes local RLCTs exactly for any two-dimensional model whose Kullback-Leibler distance is contact equivalent to a polynomial, derive a bound on its complexity, and demonstrate its effectiveness for a broad class of models, with applications including polynomial neural networks. Beyond providing ground truth to calibrate sampling-based estimators, exact computation reveals algebraic structure in learning coefficients that sampling cannot and out-speeds it in the shallow regime.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Symbolic Computation (cs.SC); Algebraic Geometry (math.AG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.20183 — 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 2026-10-18T11:47:43.341Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).