On Optimal Learning With Random Features.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 35235527.
- Also identified by DOI 10.1109/TNNLS.2022.3152270.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
We consider supervised learning in a reproducing kernel Hilbert space (RKHS) using random features. We show that the optimal rate is obtained under suitable regularity conditions, and at the same time improving on the existing bounds on the number of random features required. As a straightforward extension, distributed learning in the simple setting of one-shot communication is also considered that achieves the same optimal rate.