Metraipolis › archive › dc_da7acb604ed5

Statistical Gains from Looped Estimation under Parameter Budgets — arXiv:2609.25778

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25778
License (as archived)
CC0-1.0
Archived
2026-10-08T15:08:32.979Z
SHA-256 of the archived text
d0544975836f5ba8deb663e56582a2fceaa798cd182ca6308d07062536cc5320
Stable URL of this page
https://metraipolis.com/documento/dc_da7acb604ed5

How to cite

Statistical Gains from Looped Estimation under Parameter Budgets — arXiv:2609.25778 — arXiv (en), https://arxiv.org/abs/2609.25778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da7acb604ed5 (Metraipolis archive dc_da7acb604ed5, sha256 d0544975836f5ba8deb663e56582a2fceaa798cd182ca6308d07062536cc5320)
BibTeX
@misc{dcda7acb604ed5,
  title = {Statistical Gains from Looped Estimation under Parameter Budgets — arXiv:2609.25778},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25778},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da7acb604ed5; sha256 d0544975836f5ba8deb663e56582a2fceaa798cd182ca6308d07062536cc5320},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Memory constraints in artificial intelligence motivate accurate function approximation with fewer parameters. We study looping, which repeatedly composes one update function with shared parameters; each output becomes the next input. A looped Transformer, for example, reuses one block, whereas its conventional untied counterpart uses separately parameterized blocks. We compare their parameter requirements for a given worst-case approximation accuracy, or equivalently, their approximation accuracy under a common budget limiting distinct trainable coefficients. We then ask whether this representational parsimony improves statistical accuracy. For general likelihood models, we establish an upper squared Hellinger risk bound for looped sieve maximum likelihood and a minimax lower bound for the jointly tuned untied family. Further loop iterations improve the approximation bound without adding parameters, while increasing computation and the fitted-class complexity bound. For targets of known Hölder smoothness, looped residual feedforward networks and post-layer-normalized Transformers attain the minimax polynomial rate up to logarithmic factors with a fixed number of bounded real parameters. At sufficiently large fixed budgets, looped worst-case risk vanishes while optimal worst-case untied risk remains bounded away from zero. The loop-to-untied risk ratio also tends to zero under specified growing-budget conditions. Regression, binary response, and energy-based generative models illustrate the theory.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.25778 — 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 2026-10-08T14:37:29.548Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).