ConceptTheory & Algos
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.
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
3Each in their own terms, from the easiest level.
Michael Sipser
A property of a proof system where only true statements can be proven.Adam Klivans
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.
Lectures that assume it
1Connections
9The lectures that define it or assume it, and the concepts next to it.