Learnability and VC Dimension

Learnability and VC Dimension. Fundamentals of Machine Learning.

Type

Web resource

Intellectual base

Web

Link

https://gradml.mit.edu/supervised/learnability_and_vc/

Cited by

1 citation across 1 artifact.

Domain-specific

• Learnable Function Class
  • Standard VC theory supplies a distribution-free finite sample bound depending on \(1/\epsilon\), \(\log(1/\delta)\), and the finite dimension—not on the uncountable cardinality of \(H\).

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:f0ed8c652951 · see in the full table