ConceptTheory & Algos
Multi-objective learning
A fine-grained version of agnostic learning where an algorithm learns a function that is simultaneously good across multiple unknown data distributions and multiple loss functions.
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.