I’m Leo Duan. I’m a statistician at University of Florida since 2018.
My research aims to build new statistical methods, theory and computational toolboxes for addressing motivating application problems in neuroscience, engineering, and transportation science. The main statistical interest is in modeling the combinatorial objects that are routinely used in science and engineering (e.g., tree graphs, clustering, signal pathways, integer flow networks, etc.). Our research generates interesting solutions at the intersection between combinatorics, optimization, and Bayesian statistics.
My CV can be found here (updated 2025 May)
Lab openning: I’m looking to advise new doctoral students to work on optimization and diffusion models. If you are currently enrolled in UF graduate program & are interested in doing research with me, send an email to li dot duan at ufl dot edu.
Prof. Jason Xu @ UCLA Biostats and I @ UF Stats are teaching a short course “Harnessing Optimization in Bayesian Inference” at JSM 2025 in Nashville Tennessee. Here’s the course information — please register if interested!
Harnessing Optimization in Bayesian Inference
Sunday, Aug 3: 8:30 AM - 12:30 PM
Bayesian methods offer intuitive frameworks for specifying generative models, quantifying uncertainty, and developing model-based extensions in applications such as multi-population studies. However, traditional Bayesian approaches often face challenges when dealing with high-dimensional data, combinatorial structures, or strict parameter constraints, which can lead to increased costs in modeling, implementation, computation and inference.
This short course introduces and discusses innovative Bayesian methodologies that directly leverage strengths from the optimization literature, significantly broadening the generality and applicability of Bayesian paradigms. These approaches enable researchers to incorporate optimization-based functions or algorithms into various aspects of Bayesian analysis. Examples include accelerated posterior computation via projection-based MCMC, optimization-based reparameterizations that circumvent combinatorial costs, optimization-induced likelihood functions for structured or constrained data, and hybrid models that combine Bayesian and optimization approaches. We will explore different aspects of this framework, including model building, algorithm development, calibration, justification, and statistical inference. The application of these methods will be illustrated through modeling of networks, multivariate time series, and longitudinal or functional data in biomedical and geospatial settings.
Selected forthcoming work (please email me for latest manuscript):
Selected recent work (pre-print and accepted):
2024 UF CLAS Fellowship for Doctoral Student Supervised
2023-2026 NSF-ATD: Geospatial Modeling and Risk Mitigation for Human Movement Dynamics under Hurricane Threats (PI)
2022 UF CLAS Faculty Travel Award
2022-2023 UFII SEED Funding Award
2021 UF Statistics Faculty Award for Doctoral Student Supervised
2018 NeurIPS Bayesian Non-parametrics Award
2015 ASA Paper Competition Award in Section on Bayesian Statistical Science
2014 Woodside Foundation Award for Contribution in Biostatistics and Epidemiology Research
August 2025, EcoSta, Tokyo Japan
August 2025, Joint Statistical Meetings, Nashville TN
June 2025, BayesComp, Singapore
May 2025, Statistical Methods in Imaging Conference, Houston, TX
Zeyu Yuwen (Expected to graduate in Spring 2025)
Yu Zheng (Expected to graduate in Fall 2025)
Cheng Zeng
Edric Tam (Postdoctoral Fellow, Stanford University)
Eleni Dilma (Biostatistician, Food and Drug Administration)
Maoran Xu (Assistant Professor, Indiana University)