424 Hits in 5.4 sec

A Nonparametric Bayesian Technique for High-Dimensional Regression [article]

Subharup Guha, Veerabhadran Baladandayuthapani
2016 arXiv   pre-print
Poisson-Dirichlet processes are utilized to detect lower-dimensional latent clusters of covariates.  ...  An adaptive nonlinear prediction model is constructed for the response, achieving a balance between model parsimony and flexibility.  ...  University of Missouri, USA. E-mail address: The University of Texas MD Anderson Cancer Center and Rice University, USA.  ... 
arXiv:1604.03615v1 fatcat:ve3qbix3ujfetfqfg6cfsphnuq

Event detection in Twitter: A keyword volume approach [article]

Ahmad Hany Hossny, Lewis Mitchell
2019 arXiv   pre-print
The proposed method is to binarize vectors of daily counts for each word-pair by applying a spike detection temporal filter, then use the Jaccard metric to measure the similarity of the binary vector for  ...  The volume of these keywords is tracked in real time to identify the events of interest in a binary classification scheme. We use keywords within word-pairs to capture the context.  ...  This research was fully supported by the School of Mathematical Sciences at the University of Adelaide.  ... 
arXiv:1901.00570v1 fatcat:sq7gjg76cjbhtaqrymx3ca4bce

Point process models for sequence detection in high-dimensional neural spike trains [article]

Alex H. Williams, Anthony Degleris, Yixin Wang, Scott W. Linderman
2020 arXiv   pre-print
This ultra-sparse representation of sequence events opens new possibilities for spike train modeling.  ...  We address each of these shortcomings by developing a point process model that characterizes fine-scale sequences at the level of individual spikes and represents sequence occurrences as a small number  ...  We thank the Stanford Research Computing Center for providing computational resources and support that contributed to these research results.  ... 
arXiv:2010.04875v1 fatcat:yct3m3amk5b35bu6gesgrf3rkq

A spatiotemporal nonparametric Bayesian model of multi-subject fMRI data

Linlin Zhang, Michele Guindani, Francesco Versace, Jeffrey M. Engelmann, Marina Vannucci
2016 Annals of Applied Statistics  
In our modeling approach we consider a spatiotemporal linear regression model and specifically account for the between-subjects heterogeneity in neuronal activity via a spatially informed multi-subject  ...  We show on simulated data that variational Bayes inference achieves satisfactory results at more reduced computational costs than using MCMC, allowing scalability of our methods.  ...  The MCMC algorithm combines Metropolis-Hastings (MH) schemes that use the add-delete-swap moves [Savitsky, Vannucci and Sha (2011) ] with sampling algorithms for hierarchical Dirichlet process (HDP) models  ... 
doi:10.1214/16-aoas926 fatcat:skhecsebqffchovqbpqjhs33p4

Spatiotemporal Clustering with Neyman-Scott Processes via Connections to Bayesian Nonparametric Mixture Models [article]

Yixin Wang, Anthony Degleris, Alex H. Williams, Scott W. Linderman
2022 arXiv   pre-print
They are natural models for a wide range of phenomena, ranging from neural spike trains to document streams.  ...  This construction is similar to Bayesian nonparametric mixture models like the Dirichlet process mixture model (DPMM) in that the number of latent events (i.e. clusters) is a random variable, but the point  ...  We also thank Allison Chaney and Matthew Connelly for providing the preprocessed dataset of US State Department declassified cables. This work was supported by the U.S.  ... 
arXiv:2201.05044v2 fatcat:pbkpzp7urzd6ja2yd7a4f6e6pa

Lag penalized weighted correlation for time series clustering

Thevaa Chandereng, Anthony Gitter
2020 BMC Bioinformatics  
The similarity or distance measure used for clustering can generate intuitive and interpretable clusters when it is tailored to the unique characteristics of the data.  ...  In a simulated dataset based on the biologically-motivated impulse model, LPWC is the only method to recover the true clusters for almost all simulated genes.  ...  Funding This research was supported by NSF CAREER award DBI 1553206, the NIH University of Wisconsin Carbone Cancer Center Support Grant P30 CA014520, and the UW-Madison Center for High Throughput Computing  ... 
doi:10.1186/s12859-019-3324-1 pmid:31948388 pmcid:PMC6966853 fatcat:5fa55cnrpvcg7ghlp7ueqkbdcy

A Horseshoe mixture model for Bayesian screening with an application to light sheet fluorescence microscopy in brain imaging [article]

Francesco Denti, Ricardo Azevedo, Chelsie Lo, Damian Wheeler, Sunil P. Gandhi, Michele Guindani, Babak Shahbaba
2022 arXiv   pre-print
Our approach is based on a combination of shrinkage priors - widely used in regression and multiple hypothesis testing problems - and mixture models - commonly used in model-based clustering.  ...  In contrast to the existing regularizing prior distributions, which either use the spike-and-slab prior or continuous scale mixtures, our class of priors is based on a discrete mixture of continuous scale  ...  We employ the HSP model using a Dirichlet process, reflecting the definition of Dirichlet-HS model in the spirit of Finegold and Drton (2014) .  ... 
arXiv:2106.08281v2 fatcat:p3hipo23k5azjl6ufouqllqrda

Amortized Bayesian model comparison with evidential deep learning [article]

Stefan T. Radev, Marco D'Alessandro, Ulf K. Mertens, Andreas Voss, Ullrich Köthe, Paul-Christian Bürkner
2021 arXiv   pre-print
With this work, we propose a novel method for performing Bayesian model comparison using specialized deep learning architectures.  ...  The Bayesian probabilistic framework offers a principled way to perform model comparison and extract useful metrics for guiding decisions.  ...  ACKNOWLEDGMENT This research was supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation; grant number GRK 2277 "Statistical Modeling in Psychology").  ... 
arXiv:2004.10629v4 fatcat:gpsjtnxm4bfftowftsdvqdjs7q

A universal probabilistic spike count model reveals ongoing modulation of neural variability [article]

David Liu, Mate Lengyel
2021 bioRxiv   pre-print
Here we present a universal probabilistic spike count model that eliminates these shortcomings.  ...  Our method builds on sparse Gaussian processes and can model arbitrary spike count distributions (SCDs) with flexible dependence on observed as well as latent covariates, using scalable variational inference  ...  Melkonyan for helpful feedback on the manuscript. The number of inducing points has been shown to scale favourably as O((log T ) D ) for standard Gaussian process regression models [40] .  ... 
doi:10.1101/2021.06.27.450063 fatcat:t3tohitynfamrnqrhbryj36owq

In vitro neural networks minimise variational free energy

Takuya Isomura, Karl Friston
2018 Scientific Reports  
Acknowledgements This work was supported by RIKEN Center for Brain Science (T.I.). K.J.F. is funded by a Wellcome Principal Research Fellowship (Ref: 088130/Z/09/Z).  ...  To model this source separation, we used a Markov decision process (MDP) model and a biologically plausible gradient descent on variational free energy -as a proxy for log model evidence (i.e., an evidence  ...  The generative (Markov decision process) model.  ... 
doi:10.1038/s41598-018-35221-w fatcat:noh4gkk23rcbtk7rua34pkinq4

Gravitational wave echoes through new windows

Randy S. Conklin, Bob Holdom, Jing Ren
2018 Physical Review D  
We find time delays for the first four events that are consistent with a simple model that accounts for mass and spin of the final object, while for the neutron star merger the final mass and spin are  ...  We here report on evidence for echoes from the LIGO compact binary merger events, GW151226, GW170104, GW170608, GW170814, as well as the neutron star merger GW170817.  ...  ACKNOWLEDGMENTS We are grateful for useful discussions with participants of the conference "Quantum Black  ... 
doi:10.1103/physrevd.98.044021 fatcat:ki4sdjttj5fjdmugv3c6wtjune

Neural coding of a natural stimulus ensemble: Uncovering information at sub-millisecond resolution [article]

Ilya Nemenman, Geoffrey D. Lewen, William Bialek, Rob R. de Ruyter van Steveninck
2006 arXiv   pre-print
~60ms; different patterns of spike timing represent distinct motion trajectories, and the absolute timing of spikes points to particular features of these trajectories with high precision.  ...  New experimental methods allow us to deliver more nearly natural visual stimuli, comparable to those which flies encounter in free, acrobatic flight, and new mathematical methods allow us to draw more  ...  IN thanks the Kavli Institute for Theoretical Physics and Columbia University for their support during this work, and WB thanks the Center for Theoretical Neuroscience at Columbia University for its hospitality  ... 
arXiv:q-bio/0612050v1 fatcat:mo2uunfyuve2npfcncuykt3i5a

Discovering Health Topics in Social Media Using Topic Models

Michael J. Paul, Mark Dredze, Renaud Lambiotte
2014 PLoS ONE  
This paper describes in detail a statistical topic model created for this purpose, the Ailment Topic Aspect Model (ATAM), as well as our system for filtering general Twitter data based on health keywords  ...  We describe a topic modeling framework for discovering health topics in Twitter, a social media website.  ...  We do this using topic models, which automatically infer interesting patterns in large text corpora.  ... 
doi:10.1371/journal.pone.0103408 pmid:25084530 pmcid:PMC4118877 fatcat:rky7mludgbgbpmcigayf7giudu

A semiparametric Bayesian model for comparing DNA copy numbers

Luis Nieto-Barajas, Yuan Ji, Veerabhadran Baladandayuthapani
2016 Brazilian Journal of Probability and Statistics  
The subtypes main effects are characterized by a mixture distribution whose components are assigned Dirichlet process priors.  ...  We model the subtype and sample-specific effects using a random effects mixture model.  ...  DP(a, F ) is a Dirichlet process with precision parameter a and centering measure F . We proceed with the introduction of a sampling model, followed by the priors.  ... 
doi:10.1214/15-bjps283 fatcat:kszoq7k4mfcyjpe7fea6iacbiq

Analyzing Framing through the Casts of Characters in the News

Dallas Card, Justin Gross, Amber Boydstun, Noah A. Smith
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
We present an unsupervised model for the discovery and clustering of latent "personas" (characterizations of entities).  ...  Our model simultaneously clusters documents featuring similar collections of personas.  ...  .), and a University of Washington Innovation Award (to N.A.S.).  ... 
doi:10.18653/v1/d16-1148 dblp:conf/emnlp/CardGBS16 fatcat:56aqj6ctkrb4naks7sddrznzm4
« Previous Showing results 1 — 15 out of 424 results