Fast Non-Parametric Bayesian Inference on Infinite Trees
Description
Given i.i.d. data from an unknown distribution, we consider the problem of predicting future items. An adaptive way to estimate the probability density is to recursively subdivide the domain to an appropriate data-dependent granularity. A Bayesian would assign a data-independent prior probability to "subdivide", which leads to a prior over infinite(ly many) trees. We derive an exact, fast, and simple inference algorithm for such a prior, for the data evidence, the predictive distribution, the...[Show more]
dc.contributor.author | Hutter, Marcus | |
---|---|---|
dc.coverage.spatial | Barbados | |
dc.date.accessioned | 2015-12-10T22:41:30Z | |
dc.date.created | 6-8 January 2005 | |
dc.identifier.isbn | 097273581X | |
dc.identifier.uri | http://hdl.handle.net/1885/57947 | |
dc.description.abstract | Given i.i.d. data from an unknown distribution, we consider the problem of predicting future items. An adaptive way to estimate the probability density is to recursively subdivide the domain to an appropriate data-dependent granularity. A Bayesian would assign a data-independent prior probability to "subdivide", which leads to a prior over infinite(ly many) trees. We derive an exact, fast, and simple inference algorithm for such a prior, for the data evidence, the predictive distribution, the effective model dimension, and other quantities. | |
dc.publisher | Society for Artificial Intelligence and Statistics | |
dc.relation.ispartofseries | International Conference on Artificial Intelligence and Statistics (AISTATS 2005) | |
dc.rights | Copyright Information: © The Author(s) | |
dc.source | Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics (AISTATS 2005) | |
dc.source.uri | http://www.gatsby.ucl.ac.uk/aistats | |
dc.subject | Keywords: Inference algorithm; Infinite trees; Non-parametric Bayesian; Predictive distributions; Prior probability; Probability densities; Artificial intelligence; Bayesian networks; Forestry; Inference engines; Probability density function; Trees (mathematics) | |
dc.title | Fast Non-Parametric Bayesian Inference on Infinite Trees | |
dc.type | Conference paper | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
dc.date.issued | 2005 | |
local.identifier.absfor | 080109 - Pattern Recognition and Data Mining | |
local.identifier.ariespublication | u8803936xPUB421 | |
local.type.status | Published Version | |
local.contributor.affiliation | Hutter, Marcus, College of Engineering and Computer Science, ANU | |
local.description.embargo | 2037-12-31 | |
local.bibliographicCitation.startpage | 144 | |
local.bibliographicCitation.lastpage | 151 | |
dc.date.updated | 2016-02-24T11:44:55Z | |
local.identifier.scopusID | 2-s2.0-84862594932 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Hutter_Fast_Non-Parametric_Bayesian_2005.pdf | 5.14 MB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator