Optimal Training-Time Scaling in Gradual Adaptation

Excerpt

arXiv:2608.04927v3 Announce Type: replace Abstract: 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 $\Theta(\tau^{-1})$