Algorithmic identification of probabilities is hard

DOI10.1016/j.jcss.2018.01.002zbMath1390.68360arXiv1405.5139OpenAlexW1609488243MaRDI QIDQ1747492

Santiago Figueira, Alexander Shen, Benoit Monin, Laurent Bienvenu

Publication date: 8 May 2018

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1405.5139

zbMATH Keywords

algorithmic randomnessalgorithmic learning theory

Mathematics Subject Classification ID

Computational learning theory (68Q32) Algorithmic information theory (Kolmogorov complexity, etc.) (68Q30)

Related Items (2)

Absolutely no free lunches! ⋮ Equivalences between learning of data and probability distributions, and their applications

Cites Work

• Unnamed Item
• Identification of probabilities
• Comparison of identification criteria for machine inductive inference
• Weak completeness in \(\text{E}\) and \(\text{E}_{2}\)
• Learning recursive functions: A survey
• Constructive equivalence relations on computable probability measures
• Classical recursion theory. Vol. II
• Algorithmic tests and randomness with respect to a class of measures
• Uniform test of algorithmic randomness over a general space
• An introduction to Kolmogorov complexity and its applications

This page was built for publication: Algorithmic identification of probabilities is hard