Pith. sign in

REVIEW 1 cited by

Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound

Not yet reviewed by Pith; the record is open.

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 2011.04586 v1 pith:3OXIZ7UC submitted 2020-11-09 cs.LG stat.ML

classification cs.LGstat.ML
keywords boundcompressionmarginalgorithmsboundslearningoptimalremoving
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We analyze a family of supervised learning algorithms based on sample compression schemes that are stable, in the sense that removing points from the training set which were not selected for the compression set does not alter the resulting classifier. We use this technique to derive a variety of novel or improved data-dependent generalization bounds for several learning algorithms. In particular, we prove a new margin bound for SVM, removing a log factor. The new bound is provably optimal. This resolves a long-standing open question about the PAC margin bounds achievable by SVM.

Discussion (0). Sign in 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. Quantum Learning with Tunable Loss Functions

    quant-ph 2025-08 reject novelty 5.0 of 10

    Proposes QTERM for quantum process learning, but the proof rests on an incorrect equality E[e^{γY}] = e^{γE[Y]} for measurement bits, invalidating the sample complexity and PAC claims.

Pith tools