Metraipolis › archive › dc_515cd55acd23

Optimal Training-Time Scaling in Gradual Adaptation — arXiv:2608.04927

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04927
License (as archived)
CC0-1.0
Archived
2026-10-31T11:35:25.250Z
SHA-256 of the archived text
70d09fbb899c5bf9a732acd2df6868167dff7245071b91dbf181c8a743869e6f
Stable URL of this page
https://metraipolis.com/documento/dc_515cd55acd23

How to cite

Optimal Training-Time Scaling in Gradual Adaptation — arXiv:2608.04927 — arXiv (en), https://arxiv.org/abs/2608.04927 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_515cd55acd23 (Metraipolis archive dc_515cd55acd23, sha256 70d09fbb899c5bf9a732acd2df6868167dff7245071b91dbf181c8a743869e6f)
BibTeX
@misc{dc515cd55acd23,
  title = {Optimal Training-Time Scaling in Gradual Adaptation — arXiv:2608.04927},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04927},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_515cd55acd23; sha256 70d09fbb899c5bf9a732acd2df6868167dff7245071b91dbf181c8a743869e6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04927. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In gradual adaptation, how should the training time on each task change as the number of intermediate tasks increases? We study this question for overparameterized linear regression tasks that change smoothly and share a zero-loss solution. With $N$ tasks and training time $s_N$ on each, the final learning progress converges to a continuum curve when $Ns_N\to\tau$. The limiting progress is $\Theta(\tau)$ for small $\tau$ and $\Theta(\tau^{-1})$ for large $\tau$, so both very short and very long training produce little progress. It follows that optimal per-task training times scale as $s_N^\star=\Theta(N^{-1})$, equivalently $Ns_N^\star=\Theta(1)$. Experiments on gradually rotated MNIST and a natural Yearbook time shift are consistent with less per-task training as the path is divided more finely.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04927 — 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 2026-10-31T11:24:48.802Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).