Minimax-optimal Scaling Laws in Ridge Regression via Transfer Learning
arXiv:2610.23337v1 Announce Type: cross Abstract: Pretrained models are often reused across downstream tasks, motivating the question of whether this transfer learning procedure can provide a substantial performance improvement, namely, in terms of the scaling law. We address this question in the p…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-19 04:00 · arXiv stat.ML
Minimax-optimal Scaling Laws in Ridge Regression via Transfer Learning