ConceptAI & ML
Bounding the objective value
The expected value of a function under a new distribution is lower bounded by its expected value under the old distribution minus the total variation divergence times the maximum possible value of the function.
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.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.