Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees
This story is from 2026-08-27. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2608.25513v1 Announce Type: new Abstract: Random feature methods provide a scalable approximation to kernel ridge regression (KRR), but the regularization parameter that yields the oracle learning rate depends on unknown smoothness and capacity parameters. In this work, we propose a neighbori…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-08-27 04:00 · arXiv stat.ML
Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees