The phylogenetic Indian Buffet process: a non-exchangeable nonparametric prior for latent features

Kurt T. Miller, Thomas L. Griffiths, Michael I. Jordan
Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, PMLR R6:403-410, 2008.

Abstract

Nonparametric Bayesian models are often based on the assumption that the objects being modeled are exchangeable. While appropriate in some applications (e.g., bag-of-words models for documents), exchangeability is sometimes assumed simply for computational reasons; non-exchangeable models might be a better choice for applications based on subject matter. Drawing on ideas from graphical models and phylogenetics, we describe a non-exchangeable prior for a class of nonparametric latent feature models that is nearly as efficient computationally as its exchangeable counterpart. Our model is applicable to the general setting in which the dependencies between objects can be expressed using a tree, where edge lengths indicate the strength of relationships. We demonstrate an application to modeling probabilistic choice.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR6-miller08a, title = {The phylogenetic Indian Buffet process: a non-exchangeable nonparametric prior for latent features}, author = {Miller, Kurt T. and Griffiths, Thomas L. and Jordan, Michael I.}, booktitle = {Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence}, pages = {403--410}, year = {2008}, editor = {McAllester, David A. and Myllymäki, Petri}, volume = {R6}, series = {Proceedings of Machine Learning Research}, month = {09--12 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r6/main/assets/miller08a/miller08a.pdf}, url = {https://proceedings.mlr.press/r6/miller08a.html}, abstract = {Nonparametric Bayesian models are often based on the assumption that the objects being modeled are exchangeable. While appropriate in some applications (e.g., bag-of-words models for documents), exchangeability is sometimes assumed simply for computational reasons; non-exchangeable models might be a better choice for applications based on subject matter. Drawing on ideas from graphical models and phylogenetics, we describe a non-exchangeable prior for a class of nonparametric latent feature models that is nearly as efficient computationally as its exchangeable counterpart. Our model is applicable to the general setting in which the dependencies between objects can be expressed using a tree, where edge lengths indicate the strength of relationships. We demonstrate an application to modeling probabilistic choice.}, note = {Reissued by PMLR on 09 October 2024.} }
Endnote
%0 Conference Paper %T The phylogenetic Indian Buffet process: a non-exchangeable nonparametric prior for latent features %A Kurt T. Miller %A Thomas L. Griffiths %A Michael I. Jordan %B Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2008 %E David A. McAllester %E Petri Myllymäki %F pmlr-vR6-miller08a %I PMLR %P 403--410 %U https://proceedings.mlr.press/r6/miller08a.html %V R6 %X Nonparametric Bayesian models are often based on the assumption that the objects being modeled are exchangeable. While appropriate in some applications (e.g., bag-of-words models for documents), exchangeability is sometimes assumed simply for computational reasons; non-exchangeable models might be a better choice for applications based on subject matter. Drawing on ideas from graphical models and phylogenetics, we describe a non-exchangeable prior for a class of nonparametric latent feature models that is nearly as efficient computationally as its exchangeable counterpart. Our model is applicable to the general setting in which the dependencies between objects can be expressed using a tree, where edge lengths indicate the strength of relationships. We demonstrate an application to modeling probabilistic choice. %Z Reissued by PMLR on 09 October 2024.
APA
Miller, K.T., Griffiths, T.L. & Jordan, M.I.. (2008). The phylogenetic Indian Buffet process: a non-exchangeable nonparametric prior for latent features. Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R6:403-410 Available from https://proceedings.mlr.press/r6/miller08a.html. Reissued by PMLR on 09 October 2024.

Related Material