#  Colloquium Series: David Dunson 

 



####  calendar\_today Date and Time 

 **December 1, 2025** 

 12:00PM - 01:00PM EST 

####  pin\_drop Location 

 **Science Center, Room 316**  



 

 



 

Our upcoming event for the Statistics Colloquium Series is scheduled for Monday, December 1 from 12:00 – 1:00pm (ET) and will be an in-person presentation Science Center 316. Lunch will be provided to guests following the talk. This week's speaker will be David Dunson of Statistical Science and Mathematics at Duke University.

**Interpretable AI in Scientific Applications**

AI is largely based on deep neural networks (DNNs), which tend to be massively parameterized and fitted to immense datasets. In scientific applications, we often have smaller and noisier data than are used in the most successful AI domains, and there is a critical need for interpretability, reproducibility, accurate uncertainty quantification in inferences, and the ability to reliably fit models to modest sample sizes but high-dimensional datasets. With this in mind and motivated in particular by applications in ecology and neuroscience, this talk proposes Bayesian methods for unsupervised learning of multilayer latent structures under identifiability guarantees. The proposed methods bridge between DNNs and classical latent class and model-based clustering models, also adding to the literature on stochastic block models for networks.

**David B. Dunson** is the Arts & Sciences Distinguished Professor of Statistical Science and Mathematics at Duke University. He is a leading figure in Bayesian and machine-learning methodology for complex, high-dimensional data, with deep applications in neuroscience, genomics, ecology, environmental health and more. His work has been recognized by major honors including the COPSS Presidents’ Award, the Mortimer Spiegelman Award, the George W Snedecor Award, an IMS Medallion lecture, a gold medal from the EPA, and the Mitchell Prize. His scholarly impact is reflected in **over 85,000 citations** and an **h-index of 102**. He has had a major impact on the community through advising over a 100 PhD students and a similar number of Postdoctoral Associates, who have together transformed the Bayesian statistics landscape.

In his talk, Professor Dunson draws on his distinguished record of developing statistically principled, computationally scalable models for challenging scientific problems — connecting rigorous methodology with real-world insight.



 

 



 

 

 Share on:- [     Facebook ](#)
- [     Twitter ](#)
- [     Linkedin ](#)
 


 Save: [ Add to calendar calendar\_today ](https://statistics.fas.harvard.edu/node/1636431/event-feed.ics)  Copy link link