A philosophical treatise of universal induction

DOI10.3390/E13061076zbMATH Open1296.03007arXiv1105.5721OpenAlexW2165552039WikidataQ55951231 ScholiaQ55951231MaRDI QIDQ400871FDOQ400871

Authors: Samuel Rathmanner, Marcus Hutter 

Publication date: 26 August 2014

Published in: Entropy (Search for Journal in Brave)

Abstract: Understanding inductive reasoning is a problem that has engaged mankind for thousands of years. This problem is relevant to a wide range of fields and is integral to the philosophy of science. It has been tackled by many great minds ranging from philosophers to scientists to mathematicians, and more recently computer scientists. In this article we argue the case for Solomonoff Induction, a formal inductive framework which combines algorithmic information theory with the Bayesian framework. Although it achieves excellent theoretical results and is based on solid philosophical foundations, the requisite technical knowledge necessary for understanding this framework has caused it to remain largely unknown and unappreciated in the wider scientific community. The main contribution of this article is to convey Solomonoff induction and its related concepts in a generally accessible form with the aim of bridging this current technical gap. In the process we examine the major historical contributions that have led to the formulation of Solomonoff Induction as well as criticisms of Solomonoff and induction in general. In particular we examine how Solomonoff induction addresses many issues that have plagued other inductive systems, such as the black ravens paradox and the confirmation problem, and compare this approach with other recent approaches.

Full work available at URL: https://arxiv.org/abs/1105.5721

Recommendations

• Logically reliable inductive inference
• Inductive reasoning and Kolmogorov complexity
• On universal prediction and Bayesian confirmation
• Diverse consequences of algorithmic probability
• scientific article; zbMATH DE number 67852

zbMATH Keywords

Bayes ruleinductive inferenceKolmogorov complexityOccam's razorsequence predictionSolomonoff inductionalgorithmic information theoryblack raven paradoxconfirmation theoryphilosophical issuesSolomonoff prior

Mathematics Subject Classification ID

Probability and inductive logic (03B48) Algorithmic information theory (Kolmogorov complexity, etc.) (68Q30) Logic in the philosophy of science (03A10)

Cites Work

• Merging of Opinions with Increasing Information
• A formal theory of inductive inference. Part I
• An essay towards solving a problem in the doctrine of chances. By the late Rev. Mr. Bayes, F. R. S. communicated by Mr. Price, in a letter to John Canton, A. M. F. R. S.
• Information-theoretic asymptotics of Bayes methods
• Clustering by Compression
• The Similarity Metric
• Title not available (Why is that?)
• On the Complexity of Finite Sequences
• An introduction to Kolmogorov complexity and its applications
• Complexity-based induction systems: Comparisons and convergence theorems
• Title not available (Why is that?)
• Universal artificial intelligence. Sequential decisions based on algorithmic probability.
• Adaptive online prediction by following the perturbed leader
• R. A. Fisher on the history of inverse probability. With comments by Robin L. Plackett and G. A. Barnard and a rejoinder by the author
• Open problems in universal induction \& intelligence
• A complete theory of everything (will be subjective)
• On universal prediction and Bayesian confirmation
• Convergence and loss bounds for bayesian sequence prediction
• 10.1162/1532443041827952
• The context-tree weighting method: basic properties
• Algorithmic complexity bounds on future prediction errors

Cited In (12)

• Bridging algorithmic information theory and machine learning: a new approach to kernel learning
• On Martin-Löf (non-)convergence of Solomonoff's universal mixture
• Probabilities on sentences in an expressive logic
• Solomonoff induction violates Nicod's criterion
• Hydrozip: how hydrological knowledge can be used to improve compression of hydrological data
• Logically reliable inductive inference
• On Martin-Löf Convergence of Solomonoff’s Mixture
• On the computability of Solomonoff induction and AIXI
• A generalized characterization of algorithmic probability
• On the computability of Solomonoff induction and knowledge-seeking
• Putnam's diagonal argument and the impossibility of a universal learning machine
• A circuit complexity formulation of algorithmic information theory

This page was built for publication: A philosophical treatise of universal induction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q400871)