ConceptAI & ML
Local minima mitigation heuristics
Repeating optimization from different random initial conditions and picking the best result to avoid getting stuck in suboptimal local minima.
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
4The lectures that define it or assume it, and the concepts next to it.