Metraipolis › archive › dc_20fbcd394e81

Certifying Retraining Regret through Residual Structure — arXiv:2610.41410

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41410
License (as archived): CC0-1.0
Archived: 2026-11-02T07:50:48.248Z
SHA-256 of the archived text: 7d3bcae14663139b27d0534f14ce3d0292e43048a4557aab1d70b00adece6db0
Stable URL of this page: https://metraipolis.com/documento/dc_20fbcd394e81

How to cite

Certifying Retraining Regret through Residual Structure — arXiv:2610.41410 — arXiv (en), https://arxiv.org/abs/2610.41410 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20fbcd394e81 (Metraipolis archive dc_20fbcd394e81, sha256 7d3bcae14663139b27d0534f14ce3d0292e43048a4557aab1d70b00adece6db0)

BibTeX

@misc{dc20fbcd394e81,
  title = {Certifying Retraining Regret through Residual Structure — arXiv:2610.41410},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41410},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20fbcd394e81; sha256 7d3bcae14663139b27d0534f14ce3d0292e43048a4557aab1d70b00adece6db0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41410. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We certify a fixed ridge predictor's regret against full-feature retraining over every continuous completion of an interval-valued table. Our main theorem gives verifiable original-row residual conditions for a uniform error bound independent of nuisance-feature scale and rank, with an asymptotically sharp leading constant and quantitative leakage stability. Full-rank constructions separate certification dimension from feature dimension, including examples requiring directions beyond the candidate. Observed-row anchors make the conditions computable, while exact row geometry and global search return valid upper bounds and feasible original-table witnesses. A finite-scale contraction and common-domain moment fallback implement the structural result. Four real-world tasks retain all model features and certify twenty rank-three instances to width $10^{-5}$. Their primary median widths improve over centered moments. Joint residual refinement additionally certifies all twenty new response-independent masks to the same precision within 76.21 seconds. For a concrete fixed-point predictor contract, pure energy certifies thirteen of fifteen stopping decisions in ten seconds, versus five for moments. Refinement certifies all fifteen within 91.68 seconds at the same objective threshold.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41410 — 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 2026-11-02T07:40:00.188Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).