The phylogenetic Indian buffet process: A non-exchangeable nonparametric prior for latent features Export

@article{citeulike:3360766, 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-ofwords 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.}, author = {Miller, K. T. and Griffiths, T. L. and Jordan, M. I.}, booktitle = {Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI 2008)}, citeulike-article-id = {3360766}, citeulike-linkout-0 = {http://cocosci.berkeley.edu/publications.php?topic=Nonparametric%20Bayesian%20Models}, keywords = {bayesian, buffet, indian, phylogenetic, process}, posted-at = {2008-11-14 15:57:47}, priority = {2}, title = {The phylogenetic Indian buffet process: A non-exchangeable nonparametric prior for latent features}, url = {http://cocosci.berkeley.edu/publications.php?topic=Nonparametric%20Bayesian%20Models}, year = {2008} }

TY - JOUR ID - citeulike:3360766 L3 - citeulike-article-id:3360766 N2 - Nonparametric Bayesian models are often based on the assumption that the objects being modeled are exchangeable. While appropriate in some applications (e.g., bag-ofwords 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. TI - The phylogenetic Indian buffet process: A non-exchangeable nonparametric prior for latent features T2 - Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI 2008) KW - bayesian KW - buffet KW - indian KW - phylogenetic KW - process AU - Miller, KT AU - Griffiths, TL AU - Jordan, MI PY - 2008/// UR - http://cocosci.berkeley.edu/publications.php?topic=Nonparametric%20Bayesian%20Models ER -