Metraipolis › archive › dc_dd80cb999e85

Optimization Geometry of Equivalent Brownian RKHS Representations — arXiv:2609.21693

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21693
License (as archived)
CC0-1.0
Archived
2026-10-10T01:45:11.139Z
SHA-256 of the archived text
de23110969a63dfd29eebb6a7b42cb3f576254023f2fcf6944c8196981df4c19
Stable URL of this page
https://metraipolis.com/documento/dc_dd80cb999e85

How to cite

Optimization Geometry of Equivalent Brownian RKHS Representations — arXiv:2609.21693 — arXiv (en), https://arxiv.org/abs/2609.21693 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd80cb999e85 (Metraipolis archive dc_dd80cb999e85, sha256 de23110969a63dfd29eebb6a7b42cb3f576254023f2fcf6944c8196981df4c19)
BibTeX
@misc{dcdd80cb999e85,
  title = {Optimization Geometry of Equivalent Brownian RKHS Representations — arXiv:2609.21693},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21693},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd80cb999e85; sha256 de23110969a63dfd29eebb6a7b42cb3f576254023f2fcf6944c8196981df4c19},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21693. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Equivalent finite parameterizations can represent the same functions and intrinsic norm yet induce different optimization algorithms. We study this effect in a controlled finite Brownian RKHS with nodal, increment, and spectral coordinates. Classical finite-element, RKHS-interpolation, Brownian-covariance, and mixed-boundary DCT identities make the shared hypothesis class, Brownian energy, approximation operator, and coordinate maps explicit. Our main results concern the optimization geometry of this fixed model. With mapped initialization, identical scalar steps, and identical minibatches, nodal and spectral GD/SGD have exactly the same mapped trajectories. Increment GD is an explicit Euler step for the constant Brownian/Sobolev metric, with factor $1/h$. For Brownian-regularized least squares, $\kappa_2(\mathbf H_{\mathrm{inc}})\le1+A/\rho$, independently of grid resolution $G$ for fixed $A$, $\rho>0$, and the stated normalization. Under the stated standard-Adam convention, the universal orthogonal equivariance group is exactly the signed permutations; the block DCT-VIII transform is not one. Float64 tests over five grids numerically verify the finite identities, mapped one-layer and recursive trajectories, conditioning predictions, and theorem-matched Adam separation. Thus coordinate effects are isolated without changing the represented functions, intrinsic regularizer, or approximation space.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.21693 — 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 2026-10-10T01:14:16.644Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).