arxiv
PublishedMay 12, 2026 at 4:00 AM
Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels
Publisher summary· verbatim
arXiv:2509.20294v4 Announce Type: replace Abstract: We study spectral algorithms in the setting where kernels are learned from data. We introduce the effective span dimension (ESD), an alignment-sensitive complexity measure that depends jointly on the signal, spectrum, and noise level $\sigma^2$. Th
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗