Pith. sign in

REVIEW 1 cited by

Dimension-free uniform concentration bound for logistic regression

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 2405.18055 v5 pith:PVNKB24K submitted 2024-05-28 math.ST stat.MLstat.TH

Shogo Nakakita This is my paper · ORCID
classification math.STstat.MLstat.TH
keywords bounduniformconcentrationdimension-freeexpansionlogisticregressionapproach
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We provide a novel dimension-free uniform concentration bound for the empirical risk function of constrained logistic regression. Our bound yields a milder sufficient condition for a uniform law of large numbers than conditions derived by the Rademacher complexity argument and McDiarmid's inequality. The derivation is based on the PAC-Bayes approach with second-order expansion and Rademacher-complexity-based bounds for the residual term of the expansion.

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. Improved generalization bounds for binary linear classification via isoperimetry

    stat.ML 2025-05 conditional novelty 6.0 of 10

    Uniform generalization errors in binary linear classification concentrate around their expectation at O(1/sqrt(n)) rates under unbounded Lipschitz losses, via new log-Sobolev inequalities for (Y_i X_i, Y_i).

Pith tools