Filters








34 Hits in 4.8 sec

Nested Hierarchical Dirichlet Processes for Multi-Level Non-Parametric Admixture Modeling [article]

Lavanya Sita Tekumalla, Priyanka Agrawal, Indrajit Bhattacharya
2015 arXiv   pre-print
The Hierarchical Dirichlet Process (HDP), is an extension of DP for grouped data, often used for non-parametric topic modeling, where each group is a mixture over shared mixture densities.  ...  However, the nDP and nCRF do not allow sharing of distributions as required in many applications, motivating the need for multi-level non-parametric admixture modeling.  ...  Conclusions In this paper, we have proposed the the nested Hierarchical Dirichlet Process as a prior for multi-level admixture modeling.  ... 
arXiv:1508.06446v2 fatcat:sdddi4wlqnbylez5lcxeaq5fr4

Nested Hierarchical Dirichlet Process for Nonparametric Entity-Topic Analysis [chapter]

Priyanka Agrawal, Lavanya Sita Tekumalla, Indrajit Bhattacharya
2013 Lecture Notes in Computer Science  
The Hierarchical Dirichlet Process (HDP) is a Bayesian nonparametric prior for grouped data, such as collections of documents, where each group is a mixture of a set of shared mixture densities, or topics  ...  Making use of a nested Chinese Restaurant Franchise (nCRF) representation for the nested HDP, we propose a collapsed Gibbs sampling based inference algorithm for the model.  ...  For such problems, we have proposed as a prior distribution the nested Hierarchical Dirichlet Process, which consists of two levels of Hierarchical Dirichlet Processes, where one is the base distribution  ... 
doi:10.1007/978-3-642-40991-2_36 fatcat:5aehsmfoorbrvlbbkfj4ias5de

Scalable training of hierarchical topic models

Jianfei Chen, Jun Zhu, Jie Lu, Shixia Liu
2018 Proceedings of the VLDB Endowment  
In this paper, we study the hierarchical latent Dirichlet allocation (hLDA) model which is a powerful nonparametric Bayesian HTM.  ...  As a natural extension of flat topic models, hierarchical topic models (HTMs) are able to learn topics of different levels of abstraction, which lead to deeper understanding and better generalization than  ...  We thank Arnab Bhadury for his help in proofreading the paper.  ... 
doi:10.14778/3192965.3192972 fatcat:j5wljut2ove35pp7hybjrvms54

Scalable Inference for Nested Chinese Restaurant Process Topic Models [article]

Jianfei Chen, Jun Zhu, Jie Lu, Shixia Liu
2017 arXiv   pre-print
Hierarchical Latent Dirichlet Allocation (hLDA) is a popular instance of nCRP topic models.  ...  Nested Chinese Restaurant Process (nCRP) topic models are powerful nonparametric Bayesian methods to extract a topic hierarchy from a given text corpus, where the hierarchical structure is automatically  ...  the Dirichlet Process Mixture Model (DPMM) [14] .  ... 
arXiv:1702.07083v1 fatcat:hgrujxkaszdsbptewxryl5tcl4

A nonparametric HMM for genetic imputation and coalescent inference [article]

Lloyd T. Elliott, Yee Whye Teh
2016 arXiv   pre-print
We develop a new nonparametric model of genetic sequence data, based on the hierarchical Dirichlet process, which supports these self transitions and nonhomogeneity.  ...  model fastPHASE, which can itself be seen as a parametric truncation of our model.  ...  Acknowledgements We thank the Gatsby Charitable Foundation for funding. We also thank Chris Holmes and Ioanna Manolopoulou for helpful discussion.  ... 
arXiv:1611.00544v1 fatcat:73yv7ivnfffrngnliq5angq2f4

Mixed Membership Stochastic Blockmodels

Edoardo M Airoldi, David M Blei, Stephen E Fienberg, Eric P Xing
2008 Journal of machine learning research  
This model extends blockmodels for relational data to ones which capture mixed membership latent relational structure, thus providing an object-specific low-dimensional representation.  ...  Analyzing such data with probabilisic models can be delicate because the simple exchangeability assumptions underlying many boilerplate models no longer hold.  ...  To maintain mixed membership of nodes to groups/blocks in such setting, we need to sample them from a hierarchical Dirichlet process (Teh et al., 2006) , rather than from a Dirichlet Process (Escobar  ... 
pmid:21701698 pmcid:PMC3119541 fatcat:lcohmonivfgzbk4sapnsf4f2py

Mixed membership stochastic blockmodels [article]

Edoardo M Airoldi, David M Blei, Stephen E Fienberg, Eric P Xing
2007 arXiv   pre-print
This model extends blockmodels for relational data to ones which capture mixed membership latent relational structure, thus providing an object-specific low-dimensional representation.  ...  Analyzing such data with probabilisic models can be delicate because the simple exchangeability assumptions underlying many boilerplate models no longer hold.  ...  A recent extension of this model relaxed the finite-cardinality assumption on the latent clusters, via a nonparametric hierarchical Bayesian formalism based on the Dirichlet process prior (Kemp et al.  ... 
arXiv:0705.4485v1 fatcat:3okt3waeyfgx5par5rkvc3fvq4

Tracing the evolution of aneuploid cancers by multiregional sequencing with CRUST

Subhayan Chattopadhyay, Jenny Karlsson, Anders Valind, Natalie Andersson, David Gisselsson
2021 Briefings in Bioinformatics  
This renders a reliable clonal reconstruction well adapted to multi-regionally sampled solid tumors, which are often aneuploid and contaminated by non-cancer cells.  ...  We developed a semi-supervised algorithm that tracks variant calls through multi-sample spatiotemporal tumor data.  ...  We would also like to thank the Swegene Centre for Integrative Biology at Lund University (SCIBLU) for assistance.  ... 
doi:10.1093/bib/bbab292 pmid:34343239 pmcid:PMC8981300 fatcat:vgjspskpu5aj3and6dr4ynsboe

Genetic Signatures of Demographic Changes in an Avian Top Predator during the Last Century: Bottlenecks and Expansions of the Eurasian Eagle Owl in the Iberian Peninsula

Eva Graciá, Joaquín Ortego, José Antonio Godoy, Juan Manuel Pérez-García, Guillermo Blanco, María del Mar Delgado, Vincenzo Penteriani, Irene Almodóvar, Francisco Botella, José Antonio Sánchez-Zapata, João Pinto
2015 PLoS ONE  
However, we did not find genetic signatures for a recent bottleneck, which may indicate that population declines were not severe enough to leave PLOS ONE |  ...  We found moderate levels of differentiation among the studied subpopulations and Bayesian analyses revealed the existence of three genetic clusters that grouped subpopulations from central, south-western  ...  Further thanks go to Santiago García-Martínez and Laura Soriano, for their help with laboratory work.  ... 
doi:10.1371/journal.pone.0133954 pmid:26230922 pmcid:PMC4521928 fatcat:2o5yd3qs3jexvhapbm74nt6k6i

Modeling topic control to detect influence in conversations using nonparametric topic models

Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik, Deborah A. Cai, Jennifer E. Midberry, Yuanxin Wang
2013 Machine Learning  
To capture who introduces new topics in conversations, we introduce SITS-Speaker Identity for Topic Segmentation-a nonparametric hierarchical Bayesian model that is capable of discovering (1) the topics  ...  Identifying influential speakers in multi-party conversations has been the focus of research in communication, sociology, and psychology for decades.  ...  Oard, Earl Wagner, and Marilyn Walker for helpful discussions.  ... 
doi:10.1007/s10994-013-5417-9 fatcat:swdpnkw6dbfjdh4sasi7jpqpy4

BEAST 2.5: An Advanced Software Platform for Bayesian Evolutionary Analysis [article]

Remco Bouckaert, Timothy G Vaughan, Joelle Barido-Sottani, Sebastian Duchene, Mathieu Fourment, Alexandra Gavryushkina, Joseph Heled, Graham Jones, Denise Kuhnert, Nicola de Maio, Michael Matschiner, Fabio K Mendes (+13 others)
2018 bioRxiv   pre-print
Advanced computational software packages that allow robust development of compatible (sub-)models which can be composed into a full model hierarchy have played a key role in these developments.  ...  Including all relevant data into a single joint model is very challenging both conceptually and computationally.  ...  multi-gamma & relaxed gamma [23] substBMA site model Dirichlet mixture model for site partitions [8] Clock model : FLC molecular clock model strict and relaxed clocks within local clock model  ... 
doi:10.1101/474296 fatcat:teo5uyygrbemhhkqsknvp7o2om

BEAST 2.5: An advanced software platform for Bayesian evolutionary analysis

Remco Bouckaert, Timothy G. Vaughan, Joëlle Barido-Sottani, Sebastián Duchêne, Mathieu Fourment, Alexandra Gavryushkina, Joseph Heled, Graham Jones, Denise Kühnert, Nicola De Maio, Michael Matschiner, Fábio K. Mendes (+14 others)
2019 PLoS Computational Biology  
Advanced computational software packages that allow robust development of compatible (sub-)models which can be composed into a full model hierarchy have played a key role in these developments.  ...  Including all relevant data into a single joint model is very challenging both conceptually and computationally.  ...  Furthermore, nested sampling can be used to provide a posterior sample, and, for some cases where standard MCMC can get stuck in a mode of a multi-modal posterior, nested sampling can produce consistent  ... 
doi:10.1371/journal.pcbi.1006650 fatcat:oay3txtm3zd75dyxzc6iekjypa

On Fitting Finite Dirichlet Mixture Using ECM and MML [chapter]

Nizar Bouguila, Djemel Ziou
2005 Lecture Notes in Computer Science  
Numerical results are illustrated for the models under consideration. 2 Pair-copula constructions of multiple dependence.  ...  Fluid queue models play a vital role in the performance analysis of computer and telecommunication networks.  ...  It can be applied to two-level as well as multi-level symmetrical and asymmetrical designs.  ... 
doi:10.1007/11551188_19 fatcat:gtzi5u6emvfyxea3zbklobnvom

TwiSE at SemEval-2016 Task 4: Twitter Sentiment Classification

Georgios Balikas, Massih-Reza Amini
2016 Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)  
I am grateful for his support and advice. Our discussions and brainstorming during all these years have deeply influenced me.  ...  In [159] , the authors propose a four-level hierarchical structure where the latent topics of paragraphs are decided after performing a nested word-based LDA operation.  ...  Also, [29] proposed the Syntactic Topic Model whose goal is to integrate the text semantics and the syntax in a non-parametric topic model.  ... 
doi:10.18653/v1/s16-1010 dblp:conf/semeval/BalikasA16 fatcat:w7o56n5ny5hkjgtnqghp2sdeua

New Method for Calculating Causal Relationships (At: XXIII International Biometric Conference, Montréal, Québec, Canada, page 49)

Ilija Barukčić
2006 Zenodo  
A new method for calculating causal relationships has been presented at this conference.  ...  Cowen, University of Victoria TH22.4 An Analysis of Clustered Survival Data Using a Nonparametric Bayesian Hierarchical Model with a Dirichlet Process Prior S.O.M.  ...  Hong, Catholic University of Korea 10:45 11:00 TH9.4 Choice between Semi- Parametric Markov and Non- Markov Multi-state Models from Coarsened Observations: Application to Dementia D.  ... 
doi:10.5281/zenodo.3902085 fatcat:fiwpmehgwzbwnfc6ths447hk7i
« Previous Showing results 1 — 15 out of 34 results