Pub Date : 2024-08-05DOI: 10.1080/10618600.2024.2388543
Snigdha Das, Yabo Niu, Yang Ni, Bani K. Mallick, Debdeep Pati
Posterior computation in hierarchical Dirichlet process (HDP) mixture models is an active area of research in nonparametric Bayes inference of grouped data. Existing literature almost exclusively f...
{"title":"Blocked Gibbs sampler for hierarchical Dirichlet processes","authors":"Snigdha Das, Yabo Niu, Yang Ni, Bani K. Mallick, Debdeep Pati","doi":"10.1080/10618600.2024.2388543","DOIUrl":"https://doi.org/10.1080/10618600.2024.2388543","url":null,"abstract":"Posterior computation in hierarchical Dirichlet process (HDP) mixture models is an active area of research in nonparametric Bayes inference of grouped data. Existing literature almost exclusively f...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141899851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-05DOI: 10.1080/10618600.2024.2388605
Yizhen Xu, Joseph Hogan, Michael Daniels, Rami Kantor, Ann Mwangi
The multinomial probit (MNP) (Imai and van Dyk, 2005) framework is based on a multivariate Gaussian latent structure, allowing for natural extensions to multilevel modeling. Unlike multinomial logi...
多项式概率(MNP)(Imai 和 van Dyk,2005 年)框架基于多变量高斯潜在结构,可自然扩展到多层次建模。与多项式概率(MNP)不同的是,多项式概率(MNP)是一种多变量高斯潜在结构。
{"title":"Augmentation Samplers for Multinomial Probit Bayesian Additive Regression Trees","authors":"Yizhen Xu, Joseph Hogan, Michael Daniels, Rami Kantor, Ann Mwangi","doi":"10.1080/10618600.2024.2388605","DOIUrl":"https://doi.org/10.1080/10618600.2024.2388605","url":null,"abstract":"The multinomial probit (MNP) (Imai and van Dyk, 2005) framework is based on a multivariate Gaussian latent structure, allowing for natural extensions to multilevel modeling. Unlike multinomial logi...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141899848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-15DOI: 10.1080/10618600.2024.2379349
Xuefei Cao, Shijia Wang, Yongdao Zhou
Approximate Bayesian computation (ABC) is a class of Bayesian inference algorithms that targets problems with intractable or unavailable likelihood functions. It uses synthetic data drawn from the ...
{"title":"Using early rejection Markov chain Monte Carlo and Gaussian processes to accelerate ABC methods","authors":"Xuefei Cao, Shijia Wang, Yongdao Zhou","doi":"10.1080/10618600.2024.2379349","DOIUrl":"https://doi.org/10.1080/10618600.2024.2379349","url":null,"abstract":"Approximate Bayesian computation (ABC) is a class of Bayesian inference algorithms that targets problems with intractable or unavailable likelihood functions. It uses synthetic data drawn from the ...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141730633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-11DOI: 10.1080/10618600.2024.2374585
Sally Paganin, Perry de Valpine
Posterior predictive p-values (ppps) have become popular tools for Bayesian model assessment, being general-purpose and easy to use. However, interpretation can be difficult because their distribut...
后验预测 p 值(pps)因其通用性和易用性,已成为贝叶斯模型评估的常用工具。然而,由于其分布不均,解释起来可能很困难。
{"title":"Computational methods for fast Bayesian model assessment via calibrated posterior p-values","authors":"Sally Paganin, Perry de Valpine","doi":"10.1080/10618600.2024.2374585","DOIUrl":"https://doi.org/10.1080/10618600.2024.2374585","url":null,"abstract":"Posterior predictive p-values (ppps) have become popular tools for Bayesian model assessment, being general-purpose and easy to use. However, interpretation can be difficult because their distribut...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141597631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-09DOI: 10.1080/10618600.2024.2380051
Jiajun Liang, Qian Zhang, Wei Deng, Qifan Song, Guang Lin
This work introduces a novel and efficient Bayesian federated learning algorithm, namely, the Federated Averaging stochastic Hamiltonian Monte Carlo (FA-HMC), for parameter estimation and uncertainty quantification. We establish rigorous convergence guarantees of FA-HMC on non-iid distributed data sets, under the strong convexity and Hessian smoothness assumptions. Our analysis investigates the effects of parameter space dimension, noise on gradients and momentum, and the frequency of communication (between the central node and local nodes) on the convergence and communication costs of FA-HMC. Beyond that, we establish the tightness of our analysis by showing that the convergence rate cannot be improved even for continuous FA-HMC process. Moreover, extensive empirical studies demonstrate that FA-HMC outperforms the existing Federated Averaging-Langevin Monte Carlo (FA-LD) algorithm.
{"title":"Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory","authors":"Jiajun Liang, Qian Zhang, Wei Deng, Qifan Song, Guang Lin","doi":"10.1080/10618600.2024.2380051","DOIUrl":"https://doi.org/10.1080/10618600.2024.2380051","url":null,"abstract":"This work introduces a novel and efficient Bayesian federated learning algorithm, namely, the Federated Averaging stochastic Hamiltonian Monte Carlo (FA-HMC), for parameter estimation and uncertainty quantification. We establish rigorous convergence guarantees of FA-HMC on non-iid distributed data sets, under the strong convexity and Hessian smoothness assumptions. Our analysis investigates the effects of parameter space dimension, noise on gradients and momentum, and the frequency of communication (between the central node and local nodes) on the convergence and communication costs of FA-HMC. Beyond that, we establish the tightness of our analysis by showing that the convergence rate cannot be improved even for continuous FA-HMC process. Moreover, extensive empirical studies demonstrate that FA-HMC outperforms the existing Federated Averaging-Langevin Monte Carlo (FA-LD) algorithm.","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141663962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1080/10618600.2024.2374962
Dongkyu Derek Cho, Won Chang, Jaewoo Park
Computer models play a crucial role in numerous scientific and engineering domains. To ensure the accuracy of simulations, it is essential to properly calibrate the input parameters of these models...
{"title":"Fast Computer Model Calibration using Annealed and Transformed Variational Inference","authors":"Dongkyu Derek Cho, Won Chang, Jaewoo Park","doi":"10.1080/10618600.2024.2374962","DOIUrl":"https://doi.org/10.1080/10618600.2024.2374962","url":null,"abstract":"Computer models play a crucial role in numerous scientific and engineering domains. To ensure the accuracy of simulations, it is essential to properly calibrate the input parameters of these models...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141584476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1080/10618600.2024.2374578
Israel Martínez-Hernández, Marc G. Genton
In many phenomena, data are collected on a large scale and at different frequencies. In this context, functional data analysis (FDA) has become an important statistical methodology for analyzing an...
{"title":"Functional Time Series Analysis and Visualization Based on Records","authors":"Israel Martínez-Hernández, Marc G. Genton","doi":"10.1080/10618600.2024.2374578","DOIUrl":"https://doi.org/10.1080/10618600.2024.2374578","url":null,"abstract":"In many phenomena, data are collected on a large scale and at different frequencies. In this context, functional data analysis (FDA) has become an important statistical methodology for analyzing an...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141557125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1080/10618600.2024.2374571
Benjamin Sischka, Göran Kauermann
In this paper, we propose combining the stochastic blockmodel and the smooth graphon model, two of the most prominent modeling approaches in statistical network analysis. Stochastic blockmodels are...
{"title":"Stochastic Block Smooth Graphon Model","authors":"Benjamin Sischka, Göran Kauermann","doi":"10.1080/10618600.2024.2374571","DOIUrl":"https://doi.org/10.1080/10618600.2024.2374571","url":null,"abstract":"In this paper, we propose combining the stochastic blockmodel and the smooth graphon model, two of the most prominent modeling approaches in statistical network analysis. Stochastic blockmodels are...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141597633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1080/10618600.2024.2374570
Biplab Paul, Philip T. Reiss, Erjia Cui, Noemi Foà
The starting point for much of multivariate analysis (MVA) is an n × p data matrix whose n rows represent observations and whose p columns represent variables. Some multivariate data sets, however,...
很多多元分析(MVA)的起点是一个 n×p 的数据矩阵,其中 n 行代表观测值,p 列代表变量。然而,有些多元数据集...
{"title":"Continuous-time multivariate analysis","authors":"Biplab Paul, Philip T. Reiss, Erjia Cui, Noemi Foà","doi":"10.1080/10618600.2024.2374570","DOIUrl":"https://doi.org/10.1080/10618600.2024.2374570","url":null,"abstract":"The starting point for much of multivariate analysis (MVA) is an n × p data matrix whose n rows represent observations and whose p columns represent variables. Some multivariate data sets, however,...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141597579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-08DOI: 10.1080/10618600.2024.2374960
H. Sherry Zhang, Dianne Cook, Ursula Laa, Nicolas Langrené, Patricia Menéndez
Indexes are useful for summarizing multivariate information into single metrics for monitoring, communicating, and decision-making. While most work has focused on defining new indexes for specific ...
{"title":"A Tidy Framework and Infrastructure to Systematically Assemble Spatio-temporal Indexes from Multivariate Data","authors":"H. Sherry Zhang, Dianne Cook, Ursula Laa, Nicolas Langrené, Patricia Menéndez","doi":"10.1080/10618600.2024.2374960","DOIUrl":"https://doi.org/10.1080/10618600.2024.2374960","url":null,"abstract":"Indexes are useful for summarizing multivariate information into single metrics for monitoring, communicating, and decision-making. While most work has focused on defining new indexes for specific ...","PeriodicalId":15422,"journal":{"name":"Journal of Computational and Graphical Statistics","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141597599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}