1
|
Nonparametric Bayesian modelling of longitudinally integrated covariance functions on spheres. Comput Stat Data Anal 2022. [DOI: 10.1016/j.csda.2022.107555] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
2
|
Affiliation(s)
| | | | - Emilio Porcu
- Khalifa University, Abu Dhabi, United Arab Emirates
| | | |
Collapse
|
3
|
Time-varying spectral matrix estimation via intrinsic wavelet regression for surfaces of Hermitian positive definite matrices. Comput Stat Data Anal 2022. [DOI: 10.1016/j.csda.2022.107477] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
4
|
Alegría A, Bissiri PG, Cleanthous G, Porcu E, White P. Multivariate isotropic random fields on spheres: Nonparametric Bayesian modeling and Lp fast approximations. Electron J Stat 2021. [DOI: 10.1214/21-ejs1842] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
Affiliation(s)
- Alfredo Alegría
- Departamento de Matemática, Universidad Técnica Federico Santa Maria, Valparaíso, Chile
| | | | - Galatia Cleanthous
- Department of Mathematics and Statistics, National University of Ireland, Maynooth
| | - Emilio Porcu
- Department of Mathematics, Khalifa University, Abu Dhabi, The United Arab Emirates
| | - Philip White
- Department of Statistics, Brigham Young University
| |
Collapse
|
5
|
Lan S, Holbrook A, Elias GA, Fortin NJ, Ombao H, Shahbaba B. Flexible Bayesian Dynamic Modeling of Correlation and Covariance Matrices. BAYESIAN ANALYSIS 2020; 15:1199-1228. [PMID: 33868547 PMCID: PMC8048134 DOI: 10.1214/19-ba1173] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Modeling correlation (and covariance) matrices can be challenging due to the positive-definiteness constraint and potential high-dimensionality. Our approach is to decompose the covariance matrix into the correlation and variance matrices and propose a novel Bayesian framework based on modeling the correlations as products of unit vectors. By specifying a wide range of distributions on a sphere (e.g. the squared-Dirichlet distribution), the proposed approach induces flexible prior distributions for covariance matrices (that go beyond the commonly used inverse-Wishart prior). For modeling real-life spatio-temporal processes with complex dependence structures, we extend our method to dynamic cases and introduce unit-vector Gaussian process priors in order to capture the evolution of correlation among components of a multivariate time series. To handle the intractability of the resulting posterior, we introduce the adaptive Δ-Spherical Hamiltonian Monte Carlo. We demonstrate the validity and flexibility of our proposed framework in a simulation study of periodic processes and an analysis of rat's local field potential activity in a complex sequence memory task.
Collapse
Affiliation(s)
- Shiwei Lan
- School of Mathematical and Statistical Sciences, Arizona State University, Tempe, AZ 85287
| | - Andrew Holbrook
- David Geffen School of Medicine, University of California-Los Angeles, Los Angeles, CA 90095
| | - Gabriel A. Elias
- Center for the Neurobiology of Learning and Memory, Department of Neurobiology and Behavior, University of California-Irvine, Irvine, CA 92697
| | - Norbert J. Fortin
- Center for the Neurobiology of Learning and Memory, Department of Neurobiology and Behavior, University of California-Irvine, Irvine, CA 92697
| | - Hernando Ombao
- Statistics Program, King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia
| | - Babak Shahbaba
- Department of Statistics, University of California-Irvine, Irvine, CA 92697
| |
Collapse
|
6
|
Holbrook AJ, Lemey P, Baele G, Dellicour S, Brockmann D, Rambaut A, Suchard MA. Massive parallelization boosts big Bayesian multidimensional scaling. J Comput Graph Stat 2020; 30:11-24. [PMID: 34168419 PMCID: PMC8218718 DOI: 10.1080/10618600.2020.1754226] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2019] [Revised: 12/10/2019] [Accepted: 03/30/2020] [Indexed: 10/24/2022]
Abstract
Big Bayes is the computationally intensive co-application of big data and large, expressive Bayesian models for the analysis of complex phenomena in scientific inference and statistical learning. Standing as an example, Bayesian multidimensional scaling (MDS) can help scientists learn viral trajectories through space-time, but its computational burden prevents its wider use. Crucial MDS model calculations scale quadratically in the number of observations. We partially mitigate this limitation through massive parallelization using multi-core central processing units, instruction-level vectorization and graphics processing units (GPUs). Fitting the MDS model using Hamiltonian Monte Carlo, GPUs can deliver more than 100-fold speedups over serial calculations and thus extend Bayesian MDS to a big data setting. To illustrate, we employ Bayesian MDS to infer the rate at which different seasonal influenza virus subtypes use worldwide air traffic to spread around the globe. We examine 5392 viral sequences and their associated 14 million pairwise distances arising from the number of commercial airline seats per year between viral sampling locations. To adjust for shared evolutionary history of the viruses, we implement a phylogenetic extension to the MDS model and learn that subtype H3N2 spreads most effectively, consistent with its epidemic success relative to other seasonal influenza subtypes. Finally, we provide MassiveMDS, an open-source, stand-alone C++ library and rudimentary R package, and discuss program design and high-level implementation with an emphasis on important aspects of computing architecture that become relevant at scale.
Collapse
Affiliation(s)
| | - Philippe Lemey
- Department of Microbiology, Immunology and Transplantation, Rega Institute, KU Leuven
| | - Guy Baele
- Department of Microbiology, Immunology and Transplantation, Rega Institute, KU Leuven
| | - Simon Dellicour
- Department of Microbiology, Immunology and Transplantation, Rega Institute, KU Leuven
| | - Dirk Brockmann
- Institute for Theoretical Biology, Humboldt University Berlin
| | - Andrew Rambaut
- Institute of Evolutionary Biology, University of Edinburgh
- Fogarty International Center, National Institutes of Health
| | - Marc A. Suchard
- Department of Biostatistics, University of California, Los Angeles
- Department of Human Genetics, University of California, Los Angeles
- Department of Biomathematics, University of California, Los Angeles
| |
Collapse
|
7
|
Chau J, von Sachs R. Intrinsic Wavelet Regression for Curves of Hermitian Positive Definite Matrices. J Am Stat Assoc 2020. [DOI: 10.1080/01621459.2019.1700129] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Affiliation(s)
- Joris Chau
- Institute of Statistics, Biostatistics, and Actuarial Sciences (ISBA), Université Catholique de Louvain, Louvain-la-Neuve, Belgium
| | - Rainer von Sachs
- Institute of Statistics, Biostatistics, and Actuarial Sciences (ISBA), Université Catholique de Louvain, Louvain-la-Neuve, Belgium
| |
Collapse
|
8
|
Chau J, Ombao H, von Sachs R. Intrinsic Data Depth for Hermitian Positive Definite Matrices. J Comput Graph Stat 2019. [DOI: 10.1080/10618600.2018.1537926] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
Affiliation(s)
- Joris Chau
- Institute of Statistics, Biostatistics, and Actuarial Sciences, Université Catholique de Louvain, Louvain-la-Neuve, Belgium
| | - Hernando Ombao
- Department of Statistics, University of California at Irvine, Irvine, CA
- Department of Applied Mathematics and Computational Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
| | - Rainer von Sachs
- Institute of Statistics, Biostatistics, and Actuarial Sciences, Université Catholique de Louvain, Louvain-la-Neuve, Belgium
| |
Collapse
|
9
|
Fiecas M, Leng C, Liu W, Yu Y. Spectral analysis of high-dimensional time series. Electron J Stat 2019. [DOI: 10.1214/19-ejs1621] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
10
|
Warnick R, Guindani M, Erhardt E, Allen E, Calhoun V, Vannucci M. A Bayesian Approach for Estimating Dynamic Functional Network Connectivity in fMRI Data. J Am Stat Assoc 2018; 113:134-151. [PMID: 30853734 PMCID: PMC6405235 DOI: 10.1080/01621459.2017.1379404] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2016] [Revised: 08/01/2017] [Indexed: 01/22/2023]
Abstract
Dynamic functional connectivity, i.e., the study of how interactions among brain regions change dynamically over the course of an fMRI experiment, has recently received wide interest in the neuroimaging literature. Current approaches for studying dynamic connectivity often rely on ad-hoc approaches for inference, with the fMRI time courses segmented by a sequence of sliding windows. We propose a principled Bayesian approach to dynamic functional connectivity, which is based on the estimation of time varying networks. Our method utilizes a hidden Markov model for classification of latent cognitive states, achieving estimation of the networks in an integrated framework that borrows strength over the entire time course of the experiment. Furthermore, we assume that the graph structures, which define the connectivity states at each time point, are related within a super-graph, to encourage the selection of the same edges among related graphs. We apply our method to simulated task-based fMRI data, where we show how our approach allows the decoupling of the task-related activations and the functional connectivity states. We also analyze data from an fMRI sensorimotor task experiment on an individual healthy subject and obtain results that support the role of particular anatomical regions in modulating interaction between executive control and attention networks.
Collapse
Affiliation(s)
- Ryan Warnick
- Department of Statistics, Rice University, Houston, TX
| | - Michele Guindani
- Department of Statistics, University of California at Irvine, Irvine, CA
| | - Erik Erhardt
- Department of Mathematics and Statistics, University of New Mexico, Albuquerque, NM
| | - Elena Allen
- Research Scientist, Medici Technologies, Albuquerque, NM
| | - Vince Calhoun
- Distinguished Professor, Departments of Electrical and Computer Engineering, University of New Mexico
| | - Marina Vannucci
- Noah Harding Professor and Chair, Department of Statistics, Rice University
| |
Collapse
|