Sign inSign in

Soundness

The property that if the input W is far from being in the class, then no proof will be convincing and the tester rejects with high probability.
as Ryan O'Donnell defines itCarnegie Mellon UniversityThe wording closest to all 3 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

3

Each in their own terms, from the easiest level.

  • Michael Sipser

    MIT · Undergraduate

    A property of a proof system where only true statements can be proven.
  • Adam Klivans

    UC Berkeley · Research

    The property of a testable learning algorithm that if the data distribution meets the required assumption (like Gaussian), the test must accept with high probability.
    • 12:37Efficient Algorithms for Reliable Machine Learning

Lectures that assume it

1

Connections

9

The lectures that define it or assume it, and the concepts next to it.

3 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.