Filters








50,828 Hits in 3.5 sec

Latent Mixture Modeling for Clustered Data [article]

Shonosuke Sugasawa, Genya Kobayashi, Yuki Kawakubo
2017 arXiv   pre-print
We adapt the mixture-of-experts model to the latent distributions, and propose a model in which each cluster-wise density is represented as a mixture of latent experts with cluster-wise mixing proportions  ...  This article proposes a mixture modeling approach to estimating cluster-wise conditional distributions in clustered (grouped) data.  ...  For modeling independent data, the mixture model with covariates was originally proposed in Jacob et al. (1991) , known as mixture-ofexperts.  ... 
arXiv:1704.05993v1 fatcat:epexpzt34rbe5osyunznh7n5ze

Mixture of Latent Trait Analyzers for Model-Based Clustering of Categorical Data [article]

Isabella Gollini, Thomas Brendan Murphy
2013 arXiv   pre-print
However, model-based clustering methods for categorical data are less standard.  ...  Model-based clustering methods for continuous data are well established and commonly used in a wide range of applications.  ...  Acknowledgements This research was supported by a Science Foundation Ireland Research Frontiers Programme Grant (06/RFP/M040) and Strategic Research Cluster Grant (08/SRC/I1407).  ... 
arXiv:1301.2167v2 fatcat:l24ja7ast5h7lorx2rbkis2yfq

A Latent Gaussian Mixture Model for Clustering Longitudinal Data [article]

Vanessa S.E. Bierling, Paul D. McNicholas
2018 arXiv   pre-print
Finite mixture models have become a popular tool for clustering. Amongst other uses, they have been applied for clustering longitudinal data and clustering high-dimensional data.  ...  In the latter case, a latent Gaussian mixture model is sometimes used.  ...  From Summary A mixture model for clustering high-dimensional longitudinal data was introduced, which has the ability to account for the longitudinal nature of the data being clustered while also providing  ... 
arXiv:1804.05133v1 fatcat:or65bynznfh3peoenfty4pn3qe

Mixture of latent trait analyzers for model-based clustering of categorical data

Isabella Gollini, Thomas Brendan Murphy
2013 Statistics and computing  
However, model-based clustering methods for categorical data are less standard.  ...  Model-based clustering methods for continuous data are well established and commonly used in a wide range of applications.  ...  Acknowledgements We would like to think the editor, associate editor and reviewers for their insightful comments and suggestions which have greatly improved this paper.  ... 
doi:10.1007/s11222-013-9389-1 fatcat:ku3aaqdcojfwbfilppuk23j7jm

A mixture of experts latent position cluster model for social network data

Isobel Claire Gormley, Thomas Brendan Murphy
2010 Statistical Methodology  
The latent position cluster model extends the latent space model to deal with network data in which clusters of actors exist -actor locations are drawn from a finite mixture model, each component of which  ...  Herein, a mixture of experts extension of the latent position cluster model is developed.  ...  The mixture of experts latent position cluster model 200 The latent position cluster model can be extended within a mixture of 201 experts framework.  ... 
doi:10.1016/j.stamet.2010.01.002 fatcat:waklz6jvyzgvjisv3teqt73dzm

Mixture of Experts Modelling with Social Science Applications [chapter]

Isobel Claire Gormley, Thomas Brendan Murphy
2011 Mixtures  
Acknowledgements We would like to thank the participants of the ICMS Workshop on Mixture Estimation and Applications for their insightful feedback on this work.  ...  This work has been supported by Science Foundation Ireland Research Frontiers grants (06/RFP/M040 and 09/RFP/MTH2367) and Clique, a Science Foundation Ireland Strategic Research Cluster grant (08/SRC/I1407  ...  a cautionary message in automatically selecting the type of mixture of experts latent position cluster model for analyzing social network data.  ... 
doi:10.1002/9781119995678.ch5 fatcat:bakxhsfs6bfpzac7v27mzzdo34

Warped Mixtures for Nonparametric Cluster Shapes [article]

Tomoharu Iwata, David Duvenaud, Zoubin Ghahramani
2014 arXiv   pre-print
The possibly low-dimensional latent mixture model allows us to summarize the properties of the high-dimensional clusters (or density manifolds) describing the data.  ...  To produce more appropriate clusterings, we introduce a model which warps a latent mixture of Gaussians to produce nonparametric cluster shapes.  ...  Acknowledgements The authors would like to thank Dominique Perrault-Joncas, Carl Edward Rasmussen, and Ryan Prescott Adams for helpful discussions.  ... 
arXiv:1408.2061v1 fatcat:b5svigdi3jhxjdq7zcgpc6ehs4

Warped Mixtures for Nonparametric Cluster Shapes [article]

Tomoharu Iwata, David Duvenaud, Zoubin Ghahramani
2013 arXiv   pre-print
The possibly low-dimensional latent mixture model allows us to summarize the properties of the high-dimensional clusters (or density manifolds) describing the data.  ...  To produce more appropriate clusterings, we introduce a model which warps a latent mixture of Gaussians to produce nonparametric cluster shapes.  ...  Acknowledgements The authors would like to thank Dominique Perrault-Joncas, Carl Edward Rasmussen, and Ryan Prescott Adams for helpful discussions.  ... 
arXiv:1206.1846v2 fatcat:vgq276gmuzhnjmc55ofbnrko2i

Model-based clustering for multidimensional social networks [article]

Silvia D'Angelo, Marco Alfò, Michael Fop
2021 arXiv   pre-print
We propose the infinite latent position cluster model for multidimensional network data, which enables model-based clustering of actors interacting across multiple social dimensions.  ...  Latent space models for network data are useful to recover clustering of the actors, as they allow to represent similarities between them by their positions and relative distances in an interpretable low  ...  The latter may be thought as a latent class analysis model for network data and it is explicitly designed to model clustering of the nodes.  ... 
arXiv:2001.05260v2 fatcat:rzrukawln5d65afew5rsxediqu

Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data

Andreas Kopf, Vincent Fortuin, Vignesh Ram Somnath, Manfred Claassen, Qing Nie
2021 PLoS Computational Biology  
Additionally, we encourage the lower dimensional latent representation of our model to follow a Gaussian mixture distribution and to accurately represent the similarities between the data points.  ...  Here we introduce the Mixture-of-Experts Similarity Variational Autoencoder (MoE-Sim-VAE), a novel generative clustering model.  ...  Acknowledgments AK thanks Florian Buettner for helpful discussions and his inspirational attitude. Author Contributions Conceptualization: Andreas Kopf, Vincent Fortuin, Manfred Claassen.  ... 
doi:10.1371/journal.pcbi.1009086 pmid:34191792 pmcid:PMC8277074 fatcat:raq7ki42fng7bd52aa7lv42u6i

Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Data [article]

Andreas Kopf, Vincent Fortuin, Vignesh Ram Somnath, Manfred Claassen
2020 arXiv   pre-print
This specific architecture allows for various modes of the data to be automatically learned by means of the experts.Additionally, we encourage the lower dimensional latent representation of our model to  ...  Here we introduce the Mixture-of-Experts Similarity Variational Autoencoder (MoE-Sim-VAE), a novel generative clustering model.The model can learn multi-modal distributions of high-dimensional data and  ...  In our model, we aim to learn the mixture components in the latent representation to be standard Gaussians z ∼ K k=0 ω k N (µ k , I) (1) where ω k are mixture coefficients, µ k are the means for each mixture  ... 
arXiv:1910.07763v3 fatcat:dtlquay3lves5gaxpbatcwoa4a

A factor mixture analysis model for multivariate binary data [article]

Silvia Cagnone, Cinzia Viroli
2010 arXiv   pre-print
The paper proposes a latent variable model for binary data coming from an unobserved heterogeneous population.  ...  The aim of the proposed model is twofold: it allows to achieve dimension reduction when the data are dichotomous and, simultaneously, it performs model based clustering in the latent space.  ...  For this reason latent class is also referred to as mixture-model clustering (McLachlan and Basford, 1988) or model-based clustering (Banfield and Raftery, 1993; Fraley and Raftery, 2002) .  ... 
arXiv:1010.2314v1 fatcat:rwhyb7tyffdqlpls7fcba5tlai

The Impact of Test and Sample Characteristics on Model Selection and Classification Accuracy in the Multilevel Mixture IRT Model

Sedat Sen, Allan S. Cohen
2020 Frontiers in Psychology  
Mixture extensions of IRT models have been proposed to account for latent heterogeneous populations, but these models are not designed to handle multilevel data structures.  ...  As yet, no studies appear to have been reported examining these issues for multilevel extensions of mixture IRT models.  ...  Mixture IRT models combine a latent class model and an IRT model in a single model.  ... 
doi:10.3389/fpsyg.2020.00197 pmid:32116973 pmcid:PMC7033749 fatcat:2kbaopuzm5hp7hxcxdzxnq372q

A tutorial on Bayesian nonparametric models

Samuel J. Gershman, David M. Blei
2012 Journal of Mathematical Psychology  
This problem appears in many settings, most prominently in choosing the number of clusters in mixture models or the number of factors in factor analysis.  ...  In this tutorial, we describe Bayesian nonparametric methods, a class of methods that side-steps this issue by allowing the data to determine the complexity of the model.  ...  Mixture models and clustering In a mixture model, each observed data point is assumed to belong to a cluster.  ... 
doi:10.1016/j.jmp.2011.08.004 fatcat:allxc5i5qbcnvazdss67z7qw3y

Latent Patient Cluster Discovery for Robust Future Forecasting and New-Patient Generalization

Ting Qian, Aaron J. Masino, James Fielding Hejtmancik
2016 PLoS ONE  
Using hearing loss progression as an example, we investigate three regression models and show that the modeling of latent clusters is a robust method for addressing the more challenging prediction scenarios  ...  Given the vast opportunities enabled by large Electronic Health Records (EHR) data and powerful resources for conducting predictive modeling, we argue that it is yet crucial to first carefully examine  ...  The MSE of the mixture of regression model decreases as the number of latent clusters is increased.  ... 
doi:10.1371/journal.pone.0162812 pmid:27636203 pmcid:PMC5026362 fatcat:m3w4a5xhbjhjlhfzofwih3glxm
« Previous Showing results 1 — 15 out of 50,828 results