Multi-accuracy
A fairness/fidelity notion for generative models requiring that, for every member of a hypothesis class, the expected loss of generated samples differs from that of real data by no more than a threshold. It is stronger than simple moment matching.
Timeline (last 90 days)
From a computational complexity perspective, the two types of tasks for discriminative models and generative models (agnostic learning and multi-accuracy) are equivalent.
The regularity lemma can yield an efficient oracle reduction that reduces the indistinguishable task (multi-accuracy) to the distinguishing task (agnostic learning).
All Facts (2)
From a computational complexity perspective, the two types of tasks for discriminative models and generative models (agnostic learning and multi-accuracy) are equivalent.
50%UnverifiedThe regularity lemma can yield an efficient oracle reduction that reduces the indistinguishable task (multi-accuracy) to the distinguishing task (agnostic learning).
50%