Solomonoff Induction Violates Nicod's Criterion
Machine Learning
2015-10-20 v1 Artificial Intelligence
Statistics Theory
Statistics Theory
Abstract
Nicod's criterion states that observing a black raven is evidence for the hypothesis H that all ravens are black. We show that Solomonoff induction does not satisfy Nicod's criterion: there are time steps in which observing black ravens decreases the belief in H. Moreover, while observing any computable infinite string compatible with H, the belief in H decreases infinitely often when using the unnormalized Solomonoff prior, but only finitely often when using the normalized Solomonoff prior. We argue that the fault is not with Solomonoff induction; instead we should reject Nicod's criterion.
Cite
@article{arxiv.1507.04121,
title = {Solomonoff Induction Violates Nicod's Criterion},
author = {Jan Leike and Marcus Hutter},
journal= {arXiv preprint arXiv:1507.04121},
year = {2015}
}
Comments
ALT 2015