(weak) Calibration is Computationally Hard
Computer Science and Game Theory
2012-02-23 v1 Artificial Intelligence
Machine Learning
Machine Learning
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.
Cite
@article{arxiv.1202.4478,
title = {(weak) Calibration is Computationally Hard},
author = {Elad Hazan and Sham Kakade},
journal= {arXiv preprint arXiv:1202.4478},
year = {2012}
}