The 2022 ISBA
World Meeting

June 26th - July 1st, Hotel Bonaventure, Montreal, Canada

About The Event


About The Event

In June 2022 Montreal will be the center of Bayesian thinking in the world as we celebrate the 30-year anniversary of ISBA. The purpose of the meeting is to bring together the diverse international community of investigators in statistics who develop and use Bayesian methods to share recent findings and to present new and challenging problems. Montreal is a city where the world comes to meet and share ideas, a city that attracts talent from around the world and is known for the warm welcome it extends to visitors.


Hotel Bonaventure, Montreal, Canada


Sunday to Friday
June 26th - July 1st

Plenary Speakers

The list of speakers

Foundational Lectures

Speaker 1

Subhashis Ghosal

North Carolina State University

Speaker 2

Steffen Lauritzen

Univeristy of Copenhagen

Speaker 3

Adrian Raftery

University of Washington

Speaker 4

Nancy Reid

University of Toronto

Keynote Lectures

Speaker 1

Francesca Dominici

Harvard University

Speaker 2

Antonio Lijoi

Bocconi University

Speaker 3

David A. Stephens

McGill University

Speaker 2

Richard Nickl

University of Cambridge

Bruno de Finetti Lecture

Speaker 1

Mike West

Duke University

Susie Bayarri Lecture

Speaker 1

Pierre Jacob

ESSEC Business School

The Program

The ISBA 2022 event schedule

Click here for a downloadable schedule.

Introduction to Bayesian Methods for Clinical Trial Design and Sample Size Determination
Time: 9 am - 5 pm
Instructors: Matthew A. Psioda & Joseph G. Ibrahim (UNC Chapel Hill)
Abstract: This short course is designed to give biostatisticians and data scientists a comprehensive overview of the use of Bayesian methods for clinical trial design and training on how these methods can be implemented using standard software. Specially, applications of methodology will be demonstrated using R, SAS or both. Part I will give a broad overview of Bayesian sample size determination with a focus on fixed sample size trials either in the phase II or the phase III setting. Focus is paid to four concepts that govern sample size determination: (1) the sampling prior that reflects knowledge about the parameter(s) in the data model, (2) the fitting prior used to analyze data once collected, (3) the criterion used as the basis of sample size determination, and (4) the strategy for monitoring, if the trial will include one or more interim analyses. For (3), a comprehensive review of Bayesian criterion for sample size determination will be given, covering such topics as Bayesian type I error rate control and power, average coverage criterion, average length criterion, and worst outcome criterion. For (4) multiple strategies will be discussed for monitoring accumulating data, including using predictive probability of success and sequential methods. Part II will focus broadly on advanced Bayesian trial designs that incorporate information borrowing. The types of designs considered fall into two broad categories: (1) designs that borrow information through the use of an informative prior specified a priori based on one or more historical datasets, and (2) designs that seek to borrow information across subgroups within a trial. Example designs of type (1) include trials where the goal may be to show that a next-generation medical device (e.g., a coronary stent) is non-inferior or superior to a previous generation of the same device, and designs that seek to extrapolate information on treatment efficacy from adult trials to the pediatric setting. Example designs of type (2) include basket trials where the goal is to make inferences regarding treatment activity for different tumor types in patients whose tumor has a genetic marker targeted by the investigational treatment.

Bayesian Modelling of Epidemics: From Population to Individual-level Models
Time: 9 am - 5 pm
Instructors: Rob Deardon & Caitlin Ward (University of Calgary)
Abstract: With the ongoing COVID-19 pandemic, there has been an understandable increase in the interest in the mathematical and statistical modelling of infectious disease epidemics. Inference for mechanistic models is made more complicated by the fact that we often have latent variables (e.g., infection times). Additionally, we often have complex heterogeneities in the population we wish to account for, since, for example, populations do not tend to mix homogeneously. This often leads to a need for spatial and/or network-based models. The Bayesian framework is ideal for such complex systems, as well as prediction from the models.
In this workshop, we will examine characteristics of, and inference for, such infectious disease models starting with the classic SIR ODE-based model, and expanding into individual-level models. The workshop will include instruction on the use of the R packages, “deSolve”, “adaptMCMC” “EpiILM” and "EpiILMCT”, to implement models and inferential methods.

Bayesian multivariate time series analysis for environmental science and neuroscience
Time: 1 pm - 5 pm
Instructors: Raquel Prado (University of California - Santa Cruz), Marco Ferreira (Virginia Tech)
Abstract: This course covers principles and methods of Bayesian dynamic modeling, focusing on multivariate time series analysis and forecasting, with methodological details of central model classes explored in a range of applications to neuroscience and environmental science. A key focus is on dynamic linear models - structure, inference, forecasting — including stationary and non-stationary time series. Starting with examples of univariate time series analysis, the course extends to linked systems of univariate series defining specific classes of multivariate models, and goes further in multivariate contexts with dynamic factor models and dynamic spatial factor models. Aspects of simulation-based computation—forward simulation for forecasting, direct, approximate and simulation-based forward-backward analysis of state-space models, and MCMC methods for models with parameters and latent states going beyond the linear/Gaussian framework—are included. The course draws on a range of examples such as analysis of troposphere temperature data, multi-channel brain signal analysis, and analysis of brain imaging data.

Using R for Bayesian Spatial and spatio-temporal health modeling
Time: 8 am - 1 pm
Instructor: Andrew B Lawson (Medical University of South Carolina)
Abstract: R is commonly use now for advanced Biostatistical applications. Bayesian spatial and spatio-temporal modeling of health data is an important topic which can be addressed using tools in R. This course is designed for those who want to cover mapping methods, and the use of a variety of software and variants in application to small area health data. The course will include theoretical input, covering selected Bayesian spatial models, but also practical elements and participants will be involved in hands-on in the use of R, BRugs, Nimble, and CARBayes in disease mapping applications. Both spatial health examples will be covered in the course as well as simple space-time modelling. Examples will range over county level respiratory cancer incidence (spatial and spatio-temporal) and Covid-19 space-time modeling in US states. The course would be suitable for those with some R experience, but who have limited experience of spatial modeling in health applications.

Introduction to Bayesian Nonparametric methods for causal inference
Time: 9 am - 5 pm
Instructors: Michael Daniels (University of Florida), Antonio Linero (University Texas Austin), Jason Roy (Rutgers School of Public Health)
Abstract: Bayesian nonparametric (BNP) methods can be used to flexibly model joint or conditional distributions, as well as functional relationships. These methods, along with causal assumptions, can be used with the g-formula for inference about causal effects. This general approach to causal inference has several possible advantages over popular semiparametric methods, including efficiency gains, the ease of causal inference on any functionals of the distribution of potential outcomes, the use of prior information, and capturing uncertainty about causal assumption via informative prior distributions. In this workshop we review BNP methods and illustrate their use for causal inference in the setting of point treatments, mediation, and semi-competing risks. We present several data examples and discuss software implementation using R. The R code and/or packages used to run the data examples will be provided to the attendees at a specific github site.

End of Short Courses


Opening Address

Foundational Lecture

Speaker: Adrian Raftery
Title: Bayesian Demography and Climate Change Assessment

Coffee Break

Foundational Lecture

Speaker: Steffen Lauritzen

Lunch Break

New frontiers in Bayesian graphical and network models
- Abhirup Datta (Johns Hopkins University): Graphical models for multivariate Gaussian processes
- Mark Coates (McGill University): Bayesian Graph Neural Networks
- Anindya Bhadra (Purdue University): Graphical Evidence
- Yuguo Chen (discussant, University of Illinois)

Advances in Approximate Bayesian Computation
- Cecilia Viscardi (University of Florence): Likelihood-free Sequential Transport Monte Carlo
- Sirio Legramanti (University of Bergamo): Concentration and robustness of discrepancy-based ABC through Rademacher complexity
- Massimiliano Tamborino (University of Warwick): Guided sequential ABC schemes for intractable Bayesian models

Perspectives on prior influence and sensitivity
- Xiao-Li Meng (Harvard University): Prior sample size extensions for assessing prior impact and prior--likelihood discordance
- Will Stephenson (MIT): Measuring the robustness of Gaussian processes to kernel choice
- Noa Kallioinen (Aalto University): Detecting and diagnosing prior and likelihood sensitivity with power-scaling

Flexible dependence structures in Bayesian nonparametrics
- Beatrice Franzolini (Agency for Science, Technology and Research): Nonparametric priors for multi-sample data: dependence and borrowing of information
- Michele Guindani (UC Irvine): Bayesian approaches for clustering distributional features in neuroimaging experiments
- Steve N. MacEachern (Ohio State U): Dependence structures for longitudinal Bayesian nonparametric models

Contributions to Environmental and Earth Sciences
- Marti Anderson (Massey University & PRIMER-e):Modelling species' responses to climate change using a flexible nonlinear Bayesian approach
- Jonathan Bradley (Florida State University): Bypassing Markov Chains for a Broad Class of Bayesian Generalized Linear Mixed Effects Models
- Bruno Sanso (University of California Santa Cruz): Non-Gaussian geostatistical models using nearest neighbors processes
- Anirban Mondal (Case Western Reserve University): A Two-Stage Adaptive Metropolis Algorithm for Bayesian Model Calibration

Contributions to Economics and Finance
- Andriy Norets (Brown University): Semiparametric Bayesian Estimation of Dynamic Discrete Choice Models
- Serge Provost (Western University): Empirical Copulas and Bayesian Modeling
- Roberto Casarin (University Ca' Foscari of Venice): Bayesian nonparametric panel Markov-switching GARCH models
- Luis Carvalho (Boston University): Latent Association Graph Inference for Binary Transaction Data

Coffee Break

Advances in Bayesian Computation and its Applications
- Tamara Broderick (Massachusetts Institute of Technology): An Automatic Finite-Data Robustness Check for Bayes and Beyond: Can Dropping a Little Data Change Conclusions?
- Sally Cripps (University of Sydney and CSIRO)
- Robert Kohn (University of New South Wales)

Bayesian approaches for complex problems in causal inference
- Arman Oganisian (Brown University): Bayesian Semiparametric Model for Sequential Decision Making in Continuous Time
- Joey Antonelli (University of Florida): Improved Inference for Doubly Robust Estimators of Heterogeneous Treatment Effects
- Samrat Roy (University of Pennsylvania): A Bayesian nonparametric approach for causal inference with multiple mediators

New developments in Bayesian econometric methods and applications
- Sylvia Frühwirth-Schnatter (Vienna University of Economics and Business): When it counts – Econometric Identification of Bayesian Factor Models with Sparse Loading Matrices
- Sylvia Kaufmann (Study Center Gerzensee): Dynamic factor models with common (drifting) stochastic trends
- Herman K. van Dijk (Erasmus University Rotterdam): A Flexible Predictive Density Combination Model for Large Financial Data Sets in Regular and Crisis Periods

Geometry and dimensionality of latent representation models
- Abel Rodriguez (University of Washington): A Bayesian Approach to Spherical Factor Analysis for Binary Data
- Shane Lubold (University of Washington): Identifying the latent space geometry of network formation models through analysis of curvature
- Catherine Calder (University of Texas at Austin): The Geometry of Continuous Latent Space Models for Network Data

Bayesian structure learning in complex settings
- Reza Mohammadi (University of Amsterdam)
- Francesco Claudio Stingo (Università degli Studi di Firenze): Bayesian Covariate-Dependent Gaussian Graphical Models with Varying Structure
- Stefano Peluso (Università degli Studi di Milano-Bicocca): Network structure learning under uncertain interventions

Contributions to Bayesian Neural Networks
- Dan Richard (University of Alberta): A Neural Network for Distributions
- Ba-Hien Tran (Eurecom): Functional Priors for Bayesian Deep Learning
- Yuexi Wang (Chicago): Data Augmentation for Bayesian Deep Learning
- Mariia Vladimirova (Inria Grenoble): Dependence between Bayesian neural network units

Coffee Break

Foundational Lecture

Speaker: Nancy Reid

Foundational Lecture

Speaker: Subhashis Ghosal
Title: Immersion posterior: Empowering Bayesians to meet frequentist targets under structural restrictions

Welcome Reception Starts

Welcome Reception Ends


Keynote Talk

Speaker: Richard Nickl
Title: Bayesian non-linear inverse problems in high-dimensions

Coffee Break

De Finetti Lecture

Speaker: Mike West
Title: Subjectivist Model Uncertainty Analysis for Prediction and Decisions
Discussants: Sylvia Frühwirth-Schnatter & Herman van Dijk

Lunch Break

Recent Development on Bayesian Information and Data Comparability
- Yu-Bo Wang (Clemson University): Leveraging Historical Data via the Marginal Likelihood Criterion
- Eric Baron (University of Connecticut): Bayesian Divide-and-Conquer Propensity Score Based Approaches for Leveraging Real World Data in Randomized Control Trials
- Ming-Hui Chen (University of Connecticut): New partition based measures for data compatibility and information gain

Inverse Problems: Practical Applications and Challenges for Bayesian Methods
- Jonas Latz (Heriot-Watt University): Bayesian Inversion with Hierarchical Random Field Priors: Computational Strategies
- Matthew Berry (University of Wollongong): MCMC and SMC algorithms for estimating parameters in Thermogravemetric Analysis
- Lassi Roininen (Lappeenranta-Lahti University of Technology): Cauchy Markov random fields for Bayesian inversion

Optimal transport meets Bayes [Endorsed by: Bayesian Nonparametrics Section]
- Hugo Lavenant (Bocconi University): Wasserstein distance between Lévy measures with applications to Bayesian nonparametrics
- Stephen Walker (University of Texas at Austin): Bayesian consistency with various metrics; including the Wasserstein
- Niloy Biswas (Harvard University): Bounding Wasserstein distance with couplings

Junior advances in Bayesian treed regression
- Vittorio Orlandi (Duke University): Density Regression with Bayesian Additive Regression Trees
- Akira Horiguchi (Duke University): Using BART to Perform Pareto Optimization and Quantify its Uncertainties
- Sameer Deshpande (University of Wisconsin--Madison): Beyond axis-aligned decisions: a new BART prior for structured categorical predictors
- Matthew Pratola (discussant, The Ohio State University)

Advances in Bayesian methods for complex data
- Bora Jin (Duke University): Scalable Gaussian Processes on Physically Constrained Domains
- Francesco Denti (Università Cattolica del Sacro Cuore, Milan): Bayesian screening via mixtures of shrinkage priors with applications to light-sheet fluorescence microscopy in brain imaging
- Gabriel Hassler (University of California, Los Angeles): Principled, practical, flexible, fast: a new approach to phylogenetic factor analysis
- Giovanni Parmigiani (discussant, Harvard University)

Contributions to Bayesian Computations 1
- Murray Pollock (Newcastle University): Bayesian Fusion
- Andrew Holbrook (UCLA): A quantum parallel Markov chain Monte Carlo
- Thomas Prescott (The Alan Turing Institute): Efficient multifidelity likelihood-free Bayesian inference with adaptive resource allocation
- Onur Teymur (University of Kent): Black Box Probabilistic Numerics

Coffee Break

New Advances in Design and Analysis of Bayesian Causal Inference
- Joseph Hogan (Brown University): Bayesian approaches to unifying causal inference from mechanistic and statistical models
- Xinyi Xu (Ohio State University): Nonparametric Bayesian Estimation of Heterogeneous Causal Effects Using Real-World Data
- Corwin Zigler (University of Texas at Austin): Bayesian Design Uncertainty in Two-Stage Propensity Score Analysis
- Fan Li (discussant, Duke University): Principal Stratification: Uses, Bayesian Inference and Software

Bayesian methods for complex dependent data with application to education and psychology
- Steven Culpepper (University of Illinois at Urbana-Champaign)
- Jean-Paul Fox (University of Twente): Bayesian covariance structure modeling of clustered data
- Xiaojing Wang (University of Connecticut): Bayesian Model Assessment for Jointly Modeling Multidimensional Response Data With Application to Computerized Testing

Sampling state-of-the-arts in Bayesian computation for large-scale applications [Endorsed by: Bayesian Computation Section]
- Kelly Moran (Los Alamos National Lab): O(N) Approximate Bayesian Gaussian Process Regression
- Akihiko Nishimura (Johns Hopkins University): Hamiltonian zigzag sampler got more momentum than its Markovian counterpart: Equivalence of two zigzags under a momentum refreshment limit
- Saifuddin Syed (University of British Columbia): Non-reversible parallel tempering on optimized paths

Bayesian Workflow
- Ingeborg Hem (NTNU): Prior elicitation for variance parameters in Bayesian hierarchical models
- Jessica Hullman (Northwestern University)
- Suchi Saria (John Hopkins University)
- Dan Simpson (discussant, Monash University)

Advances in Bayesian factor models
- Daniele Durante (Bocconi): Bayesian nonparametric factorizations of matrix-valued parameters
- Daniel Kowal (Rice University): Semiparametric Functional Factor Models with Bayesian Rank Selection
- Claire Gormley (University College Dublin): Model-based clustering of high-dimensional data via Bayesian factor models

Contributions to scalable Bayesian methods
- Neil Spencer (Harvard University): Fast Approximate BayesBag Model Selection via Taylor Expansions
- Jonathan Huggins (Boston University): Calibrated Model Criticism Using Split Predictive Checks
- Michael Kouritzin (Alberta): Detecting Stealthy Behavior within Big Data

Poster Sessions


Keynote Talk

Speaker: Francesca Dominici
Title: Data Science to Address the Health Impacts of Climate Change

Coffee Break

Bayesian Concepts and Models for Multi-omics and Multi-study Analyses [Endorsed by: Biostatstics and Pharmaceutical Statistics Section]
- Isabella Grabski (Harvard University): Bayesian Multi-Study Non-Negative Matrix Factorization for Mutational Signatures
- Veera Baladandayuthapani (University of Michigan): Bayesian strategies for multi-study integration using biological hierarchies

Bayesian Penalized Likelihood-Based Methods for High-dimensional Precision Matrices and Graphs
- Tyler McCormick (University of Washington): Using Bayesian latent Gaussian graphical models to infer symptom associations in verbal autopsies
- Willem van den Boom (University of Singapore): The G-Wishart Weighted Proposal Algorithm: Efficient Posterior Computation for Gaussian Graphical Models
- Noirrit K. Chandra (University of Texas at Austin): Bayesian Scalable Precision Factor Analysis for Massive Sparse Gaussian Graphical Models
On the uses of random discrete structures for mixture modeling and clustering
- Li Ma (Duke U): Balanced tree stick-breaking priors for covariate-dependent mixture models
- Giovanni Rebaudo (UT Austin): Graph-Aligned Random Partition Model
- Yanxun Xu (Johns Hopkins U): Bayesian Sparse Mixture Models in High Dimensions

Highlights in Bayesian Analysis: Impact and Challenges in Applications[Bayesian Analysis invited session]
- Sara Wade (University of Edinburgh): Colombian Women’s Life Patterns: A Multivariate Density Regression Approach
- Marie-Pier Côté (Université Laval): A Bayesian Approach to Modeling Multivariate Multilevel Insurance Claims in the Presence of Unsettled Claims

Recent Advances in Variational Inference Methods
- Michael Stanley Smith (Melbourne Business School, University of Melbourne): Fast and Accurate Variational Inference for Models with Many Latent Variables
- Xuejun Yu (National University of Singapore): Variational inference for cutting feedback in misspecified models
- Catherine Forbes (Monash University): Updating Variation Bayes: Fast sequential posterior inference

Contributions to Gaussian processes
- Alexander Terenin (Cambridge): Pathwise Conditioning of Gaussian Processes
- Simon Mak (Duke University): A graphical Gaussian process model for multi-fidelity emulation of expensive computer codes
- Bernardo Nipoti (Milano Bicocca): Bayesian nonparametric modelling of covariance functions on the torus with an application to the analysis of wind speed data
- Boyu Ren (McLean Hospital): A Bayesian Gaussian Process for Estimating a Causal Exposure Response Curve and its Change Points

Lunch Break

Fast Variational Bayes approaches for high-dimensional problems
- David Gunawan (University of Wollongong)
- Luca Maestrini (The Australian National University): Sparse linear mixed model selection via streamlined variational Bayes
- Minh-Ngoc Tran (University of Sydney): Information geometry in Variational Bayes

Perspectives on generalized Bayesian inference [Endorsed by: Objective Bayes Section]
- Alice Kirichenko (Warwick): Bayesian inference when the model is wrong
- Jack Jewson (Pompeu Fabra): General Bayesian Loss Function Selection and the use of Improper Models
- Nicholas Syring (Iowa State University): Recent developments in Gibbs posterior inference
- Chris Holmes (discussant, Oxford)

What's new in sports analytics?
- Luke Bornn (Zelus Analytics)
- Alexander Franks (University of California, Santa Barbara): Multi-Task Gaussian Process Models for NBA Production Curves
- Guanyu Hu (University of Missouri - Columbia): Bayesian Nonparametric Estimation for Point Processes with Spatial Homogeneity: A Spatial Analysis of NBA Shot Locations

Bayesian Deep Learning
- Vincent Fortuin (ETH Zürich): On the Importance of Priors in Bayesian Deep Learning
- Andrew Wilson (New York University): Myths and Reality in Bayesian Deep Learning
- Yingzhen Li (Imperial College London)

Savage Award (theory and methods)
- Marta Catalano (Warwick): On complex dependence structures in Bayesian nonparametrics: a distance-based approach
- Aditi Shenvi (Warwick): Non-Stratified Chain Event Graphs for Modelling Asymmetric Processes
- John O'Leary (Harvard University): Coupling and Parallelization in Statistical Inference
- Aritra Guha (U Michigan)

Contributions to clustering methods and their applications
- Brenda Betancourt (University of Florida): Priors for microclustering based on allelic partitions
- Francesco Gaffi (Bocconi University): Partially-exchangeable multilayer stochastic block models
- Tommaso Rigon (Milano-Biococca): A generalized Bayes framework for probabilistic clustering
- Louise Alamichel (Université Grenoble Alpes): Bayesian nonparametric mixtures inconsistency for the number of clusters

Coffee Break

Bayesian Inference and sensitivity analysis for partially identified models
- Paul Gustafson (University of British Columbia): Handling Partial Identification: Sensitivity Analysis, Inference, or Stuck in the Middle with Bayes?
- Jiajing Zheng (University of California, Santa Barbara)
- Antonio Linero (University of Texas at Austin): Mediation Analysis using Bayesian Tree Ensembles
- Alex D'Amour (discussant, Google Research): Bayesian Inference and Partial Identification in Multi-Treatment Causal Inference with Unobserved Confounding

Recent Advances in Bayesian Causal Graphical Models and Functional Analysis for Imaging Data
- Donatello Telesca (University of California Los Angeles): Partial Membership Models for Functional Data
- Yang Ni (Texas A&M University): Ordinal Causal Discovery
- Sharmistha Guha (Texas A&M University): Bayesian Generalized Sparse Symmetric Tensor-on-Vector Regression

Bayesian methods for local variable selection
- Marina Vannucci (Rice University)
- Jian Kang (University of Michigan): Bayesian Spatially Varying Weight Neural Networks with the Soft-Thresholded Gaussian Process Prior
- Veronika Rockova (Chicago Booth University)
- David Rossell (discussant, Universitat Pompeu Fabra in Barcelona)

Savage Award (applications)
- Augusto Fasano (Collegio Carlo Alberto): Advances in Bayesian Inference for Binary and Categorical Data
- Neil Marchant (U. Merlburn): Statistical Approaches for Entity Resolution under Uncertainty
- Valerio Perrone (Amazon Web Services): Bayesian Models for Scalable Machine Learning
- Cecilia Balocchi (U. Torino): Bayesian Nonparametric Analysis of Spatial Variation with Discontinuities Bayesian Inference via Semiparametric Variational Bayes

Contributions to Variational Inference
- Hwanwoo Kim (Chicago): A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors
- Jiaxin Shi (Microsoft Research New England): Sampling with Mirrored Stein Operators
- Dennis Prangle (Bristol): Accelerating Inference for Neural Stochastic Differential Equations with Checkpoints
- Cristian Castiglione (Università degli Studi di Padova): Approximate General Bayesian Inference via Semiparametric Variational Bayes

Contributions to Bayesian modelling 1
- David Kaplan (University of Wisconsin - Madison): Bayesian Dynamic Borrowing with Applications to Large-Scale Educational Assessments
- Jim Smith (University of Warwick & the Alan Turing Institute): A Bayesian decision support system for counteracting activities of terrorist groups
- David Frazier (Monash): Asymptotic Properties of Bayesian Synthetic Likelihood
- Pierre Wollinski (Inria): An Equivalence between Bayesian Priors and Penalties in Variational Inference

Poster Sessions


Keynote Talk

Speaker: Antonio Lijoi
Title: Discreteness and dependence: an effective interplay in Bayesian nonparametrics

Coffee Break

Bayarri Lecture

Speaker: Pierre Jacob
Title: Bayesian inference with models made of modules
Discussants: Jim Berger & Judith Rousseau

Lunch Break

Bayesian methods for design and analysis of clinical trials
- Peter Mueller (University of Texas Austin): Single arm trials with a synthetic control arm built from RWD
- Satoshi Morita (Kyoto University): Bayesian Population Finding in a Randomized Clinical Trial
- Shirin Golchi (McGill University): Assessment of design operating characteristics in Bayesian adaptive trials

Advances in Bayesian modelling of spatio-temporal extreme events
- Thomas Opitz (INRAE): Latent Gauss-Markov models for spatial and spatiotemporal conditional extremes
- Benjamin Shaby (Colorado State University): Modeling First Arrival of Migratory Birds using a Hierarchical Max-infinitely Divisible Process
- Likun Zhang (Lawrence Berkeley National Lab): Spatial scale-aware tail dependence modeling for high-dimensional spatial extremes

Scalable Bayesian methods for dependent data
- Rajarshi Guhaniyogi (Texas A&M University): Bayesian data compression for spatially correlated data
- Sanvesh Srivastava (University of Iowa): Divide-and-Conquer Bayesian Inference in Hidden Markov Models
- Feras Saad (MIT): Scalable structure learning and inference for domain-specific probabilistic programs

Advances in Bayesian modeling for functional data analysis [Endorsed by: Bayesian Nonparametrics Section]
- Alessandro Colombi (University of Milano Biococca): Block structured Gaussian graphical models for spectrometric functional data
- Huiyan Sang (Texas A&M University): Bayesian Additive Multivariate Decision Trees for Spatial Nonparametric Function Estimation on Complex Domains
- David Dunson (Duke University): Graph based Gaussian processes on restricted domains

Interventions in Complex Systems
- Nora Bello (Ohio State U.): Hierarchical Modeling of Heterogeneous Networks for Animal Production Systems
- Tim Au (Google): Inferring the Causal Impact of Online Advertising on Multiple Treated Units Using Synthetic Controls
- Hongxia Yang (Alibaba DAMO Academy): Towards the Next Generation of Artificial Intelligence with its Applications in Practice

Contributions to variable and model selection
- Maoran Xu (University of Florida): Can we do better than Spike-and-Slab? --- New theory about L1-ball priors in variable selection.
- Nicolas Bousquet (EDF): Bayesian modeling, prior compatibility and selection for extreme value models
- Jian Cao (Texas A&M University): Scalable Gaussian-process regression and variable selection using Vecchia approximations
- Matthew Heiner (Brigham Young University): Shrinkage on the Simplex: Bayesian Inference with Sparse Generalized Dirichlet Distributions

Coffee Break

Bayesian methods for network data
- Nathaniel Josephs (Yale School of Public Health): Gaussian processes using network inputs with application to the microbiome
- Arash Amini (UCLA): Hierarchical stochastic block model for community detection in multiplex networks
- Forrest Crawford (discussant, Yale School of Public Health)

Recent applications of scalable Bayesian inference using stochastic gradient MCMC [Endorsed by: Bayesian Computation Section]
- Inass Sekkat (CERMICS - Ecole des Ponts ParisTech): Removing the mini-batching error in Bayesian inference using Adaptive Langevin dynamics
- Qifan Song (Purdue University): Federated Learning with Hamiltonian Monte Carlo
- Christopher Nemeth (Lancaster University): Preferential data subsampling in stochastic gradient MCMC

Challenges in random probability models
- Rosangela H Loschi (Universidade Federal de Minas Gerais): Handling Categorical Features with Many Levels Using a Product Partition Model
- Garritt Page (Brigham Young University): Clustering and Prediction with Variable Dimension Covariates
- Mario Beraha (Politecnico di Milano and Università di Bologna): Beyond CRMs: normalized random measures with atoms’ interaction for Bayesian mixture models

Bayesian experimental design for causal inference
- Federico Castelletti (Universita' Cattolica del Sacro Cuore): Bayesian sample size determination for network structure learning
- Julius von Kügelgen (Max Planck Institute for Intelligent Systems, University of Cambridge): Active Bayesian Causal Discovery
- Jeffrey Miller (Harvard T.H. Chan School of Public Health): Bayesian Optimal Experimental Design for Inferring Causal Structure

Contributions to Bayesian neural networks 2
- Mariya Mamajiwala (UCL): Stochastically developed Langevin dynamics applied to generative adversarial networks
- Tiangang Cui (Monash): Tensorised Rosenblatt Transport for High-Dimensional Stochastic Computation
- Nadja Klein (Humboldt-Universität zu Berlin): Marginally calibrated response distributions for end-to-end learning in autonomous driving
- Gianluca Finocchio (Vienna): Posterior contraction for deep Gaussian process priors

Contributions to Methods for Genetics
- Emilie Eliseussen (Oslo): Lower-dimensional Bayesian Mallows model for rank-based unsupervised transcriptomic analysis
- Federico Camerlenghi (Milano-Bicocca): Scaled process priors for Bayesian nonparametric estimation of the unseen genetic variation
- Marco Ferreira (Virginia Tech): Bayesian analysis of GLMMs with nonlocal priors for genome-wide association studies
- Massimiliano Russo (Harvard University): Bayesian bi-clustering for temporally heterogeneous high-dimensional longitudinal data

General ISBA Assembly

Poster Sessions


Keynote Talk

Speaker: David A. Stephens

Coffee Break

Bayesian design in clinical trial and some fundamental issues
- Sujit Ghosh (North Carolina State University): Average Error Controlled Bayesian Sample Size Determination Methods
- Sudipto Banerjee (University of California, Los Angeles): Simulation-based Bayesian Sample Size Calculations Using Design and Analysis Priors in Contemporary Clinical Trials
- Lindsay Berry (Berry Consultants): A comparison of response adaptive randomization and arm dropping features in the presence of temporal drift
- Yuan Ji (discussant, University of Chicago)

Applications and Extensions of Dirichlet process Mixture models
- Scott Linderman (Stanford): Spatiotemporal Clustering with Neyman-Scott
- Enrico Bibbon (Polytechnic of Turin): Multiple latent clustering model for the inference of RNA life-cycle kinetic rates from sequencing data
- Clara Grazian (University of Sydney): Spatio-temporal stick-breaking

Some recent works on Gaussian Markov random fields and related Bayesian methods for estimation, learning, and inference
- María Dolores Ugarte (Universidad Pública de Navarra): Dealing with large data sets in spatio-temporal disease mapping
- Marcos Prates (Universidade Federal de Minas Gerais): Non-Separable Spatio-temporal Models via Transformed Multivariate Gaussian Markov Random Fields
- Ying MacNab (University of British Columbia): Some computational strategies for richly parameterized multivariate Gaussian Markov random fields

Model Uncertainty and Combination in Prediction and Decision Problems: Bayesian Frontiers [Endorsed by: Economics, Finance, and Business Section]
- Ken McAlinn (Temple University): Dynamic Bayesian predictive synthesis with large number of forecasts
- James Mitchell (Federal Reserve Bank of Cleveland): The Copula Opinion Pool: Modeling Expert Dependence
- Emily Tallman (Duke University): Decision-guided Bayesian model uncertainty analysis: Betting on better models

Contributions to Bayesian Computations 2
- Giacomo Zanella (Bocconi): Robust leave-one-out cross-validation for high-dimensional Bayesian models
- Robin Ryder (Université Paris-Dauphine): ABC-ROM: Time-series forecasting with ABC prediction uncertainty and Reduced Order Models
- Chiara Galimberti (Milano-Bicocca): Structure Learning of Mixed Graphical Models
- Chris U. Carmona (Oxford): Simultaneous Reconstruction of Spatial Frequency Fields and Sample Locations via Bayesian Semi-Modular

Contributions to Causality
- Widemberg Nobre (INSPER - Brazil): Modelling the death rate among hospitalisations during the first wave of the Coronavirus pandemic: A causal mediation approach
- Alberto Caron (University College London): Shrinkage Bayesian Causal Forests for Heterogeneous Treatment Effects Estimation
- Bart Eggen (Delft University of Technology): Bayesian sensitivity analysis for a missing data model
- Jenifer Starling (Mathematic Policy Research): Uncertainty calibration and exemplar identification for heterogeneous treatment effects with Individualized Bayesian Causal Forests (iBCF)

Lunch Break

Bayesian modelling of human migration
- Nathan G. Welch (University of Washington): Bayesian projection of international migration flows
- Emily R. Barker (University of Southampton): Bayesian estimation and forecasting of migration in Europe: From hierarchical models to panel VARs
- Jason Hilton and Martin Hinsch (University of Southampton): Bayesian calibration of a model of forced displacement
- Arkadiusz Wiśniowski (discussant, University of Manchester)

Bayesian statistics within mixed (qualitative & quantitative) methods [Endorsed by: Bayesian Education Research and Practice Section]
- Daniel Harasim (Swiss Federal Institute of Technology)
- Daniela Vasco (Griffith University)
- Samantha Low-Choy (Griffith University)

Recent Advancements in Bayesian Methods for Statistical Data Privacy
- Terrence Savitsky (U.S. Bureau of Labor Statistics): Private Tabular Survey Data Products through Synthetic Microdata Generation
- Harrison Quick (Drexel University): Differentially private synthetic data for disease mapping
- Claire Bowen (Urban Institute): Comparative Study of Differentially Private Data Synthesis Methods
- Jerome Reiter (discussant, Duke University): Discussion of Presentations

Bayesian modelling with Copulas
- Vianey Leos-Barajas (Toronto)
- Fabrizio Leisen (Nottingham): Compound vectors of subordinators and their associated positive Lévy copulas
- Luis Enrique Nieto Barajas (ITAM, Mexico City): A Bayesian semiparametric Archimedean copula

Latent Variable Models in High-dimensional Data
- Georgia Papadogeorgou (University of Florida): Covariate-informed latent interaction models: Addressing geographic & taxonomic bias in predicting bird-plant interactions
- Weining Shen (University of California, Irvine): Bayesian analysis of matrix data with applications to professional basketball game analysis
- Zhenke Wu (University of Michigan): Tree-Informed Bayesian Multi-Source Domain Adaptation

Contributions to Bayesian life sciences
- Gonzalo Mena (Oxford): On estimation of infection fatality rates with and without serological data
- Caitlin Ward (University of Calgary): Sound the alarm: modeling behavioral changes in response to epidemic intensity
- Sally Paganin (Harvard University): A hierarchical Hidden Markov Model for cancer detection
- Audrey Béliveau (University of Waterloo): Bayesian Joint Modeling of Within- and Between-Period Information in Capture-Recapture Studies of Migrating Populations

Coffee Break

Recent developments in Bayesian education
- Colin Rundel (Duke University): An overview of Bayesian computational frameworks for teaching
- Sierra Merkes (Virginia Tech): A Comparative Approach to Teaching Undergraduates
- Jingchen (Monika) Hu (Vassar College): The current state of undergraduate Bayesian education and recent developments
- Jim Albert (Bowling Green State University): Bayesian Computing in the Undergraduate Statistics Curriculum

Gaussian Process Under Manifold Assumptions: A Promising Prior for High-Dimensional Nonparametric Regression Without Sparsity?
- Cheng Li (National University of Singapore): Bayesian Fixed-domain Asymptotics for Covariance Parameters in Spatial Gaussian Process Models
- Sheng Jiang (University of California Santa Cruz): Variable Selection Consistency of Gaussian Process Regression
- Nan Wu (Duke University): Graph Laplacian based Gaussian processes on restricted domains

Model-based clustering for complex data
- Raffaele Argiento (University of Bergamo): Clustering grouped data via hierarchical mixture models
- David Dahl (Brigham Young University): Shrinking a Partition Distribution Towards a Baseline Partition, With Applications to Dependent Partitions
- Alessandra Guglielmi (Politecnico di Mliano): Repulsive mixture models for high-dimensional data

Innovative Bayesian approaches to substantive real-world challenges
- Edgar Santos Fernandez (Queensland University of Technology): Against all odds: enhancing statistical monitoring schemes using new sources of data
- Raiha Browning (Queensland University of Technology): Nonparametric discrete-time Hawkes processes in practice
- Leanna House (Virginia Tech): Modeling Populations

Contributions to MCMC
- Gareth Roberts (Warwick): Stereographic Markov chain Monte Carlo
- David Swanson (Oslo): Collapsed blocked Gibbs sampling for improved convergence in latent variable models
- Jackie Wong (University of Essex): Properties of the bridge sampler with a focus on splitting the MCMC sample
- Christian Robert (Paris Dauphine): Testing for components in finite and infinite mixtures

Contributions to Bayesian modelling
- Lucas Godoy (University of Connecticut): Flexible spatial modeling of areal data: Introducing the Hausdorff-Gaussian Spatial Process
- Antik Chakraborty (Purdue University): Orthogonal calibration via projected posteriors
- Michail Papathomas (University of St Andrews) Reliable variance matrix priors for Bayesian mixture models with Gaussian kernels for problems of moderately high-dimensionality
- Stefano Rizzelli (Università Cattolica): Frequentist asymptotics for parametric empirical Bayes

Prize Ceremony and Banquette

Local Information

Event venue and accomodation

Hotel Bonaventure, Montreal, Canada

Iconic landmark of the city, the Bonaventure offers elegance in a unique setting in Montreal. Winner of several awards for its high level of quality and service, the hotel continues to maintain its distinctive personality and character.


Montréal-Pierre Elliott Trudeau International Airport

Located 20 kilometres from downtown Montréal, with multiple highway accesses, Montreal-Trudeau has recently completed a vast expansion and modernization program. Its world-class air terminal is designed to provide you with the most efficient, comfortable and safe airport experience possible. Equipped with the latest airport technologies, it also offers a comprehensive range of services to suit all tastes and budgets.


Platinum Level

Gold Level

Silver Level

Bronze Level


Contact Us

Drop us a line if you have any questions. Requests for customized receipts or invoices are subject to a $25 USD administrative fee. Please pay your fee at and contact us at with the details for your request.

Local Organizing Committee

Scientific Committee