Abstract Number:
1120
Submission Type:
Invited Paper Session
Participants:
Li Ma (1), Li Ma (1), Long Nguyen (2), Antonio Linero (3), Linxi Liu (4)
Institutions:
(1) Duke University, N/A, (2) University of Michigan, N/A, (3) N/A, N/A, (4) Univeristy of Pittsburgh, N/A
Chair:
Session Organizer:
Speaker(s):
Session Description:
The focus of the session is on recent theoretical and methodological advances in Bayesian semi- and nonparametric inference, with particular attention given to methods that address challenges in analyzing modern high-dimensional and functional data sets under complex sampling design. In many modern problems, the target of inference (e.g. functions, distributions, covariance, etc.) contain interesting structures of a variety of nature. Bayesian semi- and nonparametric methods are a natural and powerful approach to these problems that take into account rich distributional features. Whereas classical BNP models were developed assuming a single sampling distribution that gives rise to an exchangeable data set, modern study designs often involve multiple data sets whose sampling distributions are related but distinct. Such relationships can often be characterized in a principled way through modeling hierarchical relationships. This field has undergone tremendous progress in recent years. This session will showcase some of these exciting new developments to the statistical community, and will be of particularly broad appeal to audience interested in Bayesian inference, nonparametric analysis, and applications.
The proposed session will consist of 3 talks given by speakers who are at different stages of their career, and represent a diverse professional and demographic background. They are well-respected intellectual leaders and rising stars in the field of Bayesian nonparametric inference, and will present an exciting session on this timely topic.
Session format: 3 speakers
List of speakers and their tentative titles:
Title: Posterior contraction of infinite-dimensional latent mixing measures
Speaker: Long Nguyen, Professor, Department of Statistics, University of Michigan
Title: Estimating Heterogeneous Causal Mediation Effects with Bayesian Decision Tree Ensembles
Speaker: Antonio Linero, Associate Professor, Department of Statistics, University of Texas at Austin
Title: Posterior concentration for Bayesian density trees and forests
Speaker: Linxi Liu, Assistant Professor, Department of Statistics, University of Pittsburgh
Sponsors:
No Additional Sponsor 3
International Society for Bayesian Analysis (ISBA) 2
Section on Bayesian Statistical Science 1
Theme:
Statistics and Data Science: Informing Policy and Countering Misinformation
Yes
Applied
Yes
Estimated Audience Size
Small (<80)
I have read and understand that JSM participants must abide by the Participant Guidelines.
Yes
I understand and have communicated to my proposed speakers that JSM participants must register and pay the appropriate registration fee by June 1, 2024. The registration fee is nonrefundable.
I understand