(weak) Calibration is Computationally Hard

Abstract

We show that the existence of a computationally efficient calibration algorithm, with a low weak calibration rate, would imply the existence of an efficient algorithm for computing approximate Nash equilibria - thus implying the unlikely conclusion that every problem in PPAD is solvable in polynomial time.

References in corpus (1)

• Online Learning: Beyond Regret

Cited by in corpus (1)

• Scalable Multilabel Prediction via Randomized Methods