David B. Dunson

David B. Dunson

Arts and Sciences Distinguished Professor of Statistical Science

External address: 
218 Old Chemistry Bldg, Durham, NC 27708
Internal office address: 
Box 90251, Durham, NC 27708-0251
(919) 684-8025


Development of novel approaches for representing and analyzing complex data.  A particular focus is on methods that incorporate geometric structure (both known and unknown) and on probabilistic approaches to characterize uncertainty.  In addition, a big interest is in scalable algorithms and in developing approaches with provable guarantees.

This fundamental work is directly motivated by applications in biomedical research, network data analysis, neuroscience, genomics, ecology, and criminal justice.   

Education & Training

  • Ph.D., Emory University 1997

  • B.S., Pennsylvania State University 1994

Selected Grants

Duke University Program in Environmental Health awarded by National Institutes of Health (Mentor). 2013 to 2024

HDR TRIPODS: Innovations in Data Science: Integrating Stochastic Modeling, Data Representation, and Algorithms awarded by National Science Foundation (Senior Investigator). 2019 to 2022

Reproducibility and Robustness of Dimensionality Reduction awarded by National Institutes of Health (Investigator). 2017 to 2022

An Integrated Nonparametric Bayesian and Deep Neural Network Framework for Biologically-Inspired Lifelong Learning awarded by Defense Advanced Research Projects Agency (Co Investigator). 2018 to 2022

Structured nonparametric methods for mixtures of exposures awarded by National Institutes of Health (Principal Investigator). 2018 to 2022

Probabilistic learning of structure in complex data awarded by Office of Naval Research (Principal Investigator). 2017 to 2021

CRCNS: Geometry-based Brain Connectome Analysis awarded by National Institutes of Health (Principal Investigator). 2018 to 2021

Postdoctoral Training in Genomic Medicine Research awarded by National Institutes of Health (Mentor). 2017 to 2021

Scalable probabilistic inference for huge multi-domain graphs awarded by (Principal Investigator). 2017 to 2020


Aliverti, Emanuele, et al. “Projected t-SNE for batch correction.Bioinformatics (Oxford, England), vol. 36, no. 11, June 2020, pp. 3522–27. Epmc, doi:10.1093/bioinformatics/btaa189. Full Text

Dunson, D. B., and J. E. Johndrow. “The Hastings algorithm at fifty.” Biometrika, vol. 107, no. 1, Mar. 2020, pp. 1–23. Scopus, doi:10.1093/biomet/asz066. Full Text

Duan, Leo L., et al. “Bayesian constraint relaxation.Biometrika, vol. 107, no. 1, Mar. 2020, pp. 191–204. Epmc, doi:10.1093/biomet/asz069. Full Text

Tikhonov, Gleb, et al. “Computationally efficient joint species distribution modeling of big spatial data.Ecology, vol. 101, no. 2, Feb. 2020, p. e02929. Epmc, doi:10.1002/ecy.2929. Full Text

Jauch, M., et al. “Random orthogonal matrices and the Cayley transform.” Bernoulli, vol. 26, no. 2, Jan. 2020, pp. 1560–86. Scopus, doi:10.3150/19-BEJ1176. Full Text

Ferrari, F., and D. B. Dunson. “Bayesian Factor Analysis for Inference on Interactions.” Journal of the American Statistical Association, Jan. 2020. Scopus, doi:10.1080/01621459.2020.1745813. Full Text

Dunson, D., and T. Papamarkou. “Discussion.” International Statistical Review, Jan. 2020. Scopus, doi:10.1111/insr.12375. Full Text

Camerlenghi, F., et al. “Latent nested nonparametric priors (with discussion).” Bayesian Analysis, vol. 14, no. 4, Dec. 2019, pp. 1303–56. Scopus, doi:10.1214/19-BA1169_1. Full Text

Panea, Razvan I., et al. “The whole-genome landscape of Burkitt lymphoma subtypes.Blood, vol. 134, no. 19, Nov. 2019, pp. 1598–607. Pubmed, doi:10.1182/blood.2019001880. Full Text

Lin, L., et al. “Extrinsic Gaussian processes for regression and classification on manifolds.” Bayesian Analysis, vol. 14, no. 3, Jan. 2019, pp. 887–906. Scopus, doi:10.1214/18-BA1135. Full Text


Thai, D. H., et al. “Locally convex kernel mixtures: Bayesian subspace learning.” Proceedings  18th Ieee International Conference on Machine Learning and Applications, Icmla 2019, 2019, pp. 272–75. Scopus, doi:10.1109/ICMLA.2019.00051. Full Text