Solomonoff Prediction and Occam’s Razor

Citation data:

Philosophy of Science, ISSN: 0031-8248, Vol: 83, Issue: 4, Page: 459-479

Publication Year:
2016
Usage 274
Downloads 230
Abstract Views 34
Link-outs 10
Captures 3
Readers 3
Social Media 1
Tweets 1
Citations 2
Citation Indexes 2
Repository URL:
http://philsci-archive.pitt.edu/id/eprint/12429
DOI:
10.1086/687257
Author(s):
Tom F. Sterkenburg
Publisher(s):
University of Chicago Press, The University of Chicago Press
Tags:
Arts and Humanities
Most Recent Tweet View All Tweets
article description
Algorithmic information theory gives an idealized notion of compressibility that is often presented as an objective measure of simplicity. It is suggested at times that Solomonoffprediction, or algorithmic information theory in a predictive setting, can deliver an argument to justify Occam’s razor. This article explicates the relevant argument and, by converting it into a Bayesian framework, reveals why it has no such justificatory force. The supposed simplicity concept is better perceived as a specific inductive assumption, the assumption of effectiveness. It is this assumption that is the characterizing element of Solomonoffprediction and wherein its philosophical interest lies.

This article has 0 Wikipedia mention.