Pith. sign in

REVIEW 1 cited by

Fixing an error in Caponnetto and de Vito (2007)

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1702.02982 v2 pith:J4MZLCHX submitted 2017-02-09 stat.ML cs.LGmath.STstat.TH

Danica J. Sutherland This is my paper · ORCID
classification stat.MLcs.LGmath.STstat.TH
keywords boundcaponnettoerrorvitocontainscorrectdimensionalityeffective
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The seminal paper of Caponnetto and de Vito (2007) provides minimax-optimal rates for kernel ridge regression in a very general setting. Its proof, however, contains an error in its bound on the effective dimensionality. In this note, we explain the mistake, provide a correct bound, and show that the main theorem remains true.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators

    stat.ML 2026-07 accept novelty 7.0 of 10

    RKHS adversarial training loses minimax prediction rate via noise in the mixed robustness term; noise-debiased AT restores the polynomial minimax rate up to a log factor.

Pith tools