Pith. sign in

REVIEW 1 cited by

A Computability Perspective on (Verified) Machine Learning

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 2102.06585 v1 pith:RAO52YDD submitted 2021-02-12 cs.LG cs.LO

Tonicha Crook , Jay Morgan , Arno Pauly , Markus Roggenbach This is my paper · ORCID
classification cs.LGcs.LO
keywords learningmachineverifiedcomputableperspectiveallowsanalysisassurances
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational tasks underlying verified ML in a model-agnostic way, and show that they are in principle computable.

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. Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning

    cs.LG 2025-11 conditional novelty 7.0 of 10

    For computable PAC learning, the effective VC-dimension can take any value above the VC-dimension, and every recursively enumerably representable class is nonuniformly agnostically learnable.

Pith tools