Dr. Tri Le
Assistant Professor of Mathematics and Computer Science
Program Coordinator, M.S. in Applied Data Intelligence and Machine Learning
Department of Informatics and Mathematics
- B.S., Ho Chi Minh City University of Natural Sciences
- M.S., Ho Chi Minh City University of Natural Sciences
- M.A., University of Missouri – Columbia
- Ph.D., University of Missouri – Columbia
Dr. Tri M. Le is an Assistant Professor of Mathematics and Computer Science at the Department of Informatics and Mathematics. Before joining Mercer University in 2017, he worked at the University of Nebraska-Lincoln as a Predictive/Computational Statistician with expertise in statistical software packages such as SAS, SPSS, and R.
Dr. Le’s current areas of interest include Bayesian analysis, decision theory, spatio-temporal modeling, model uncertainty and prediction, and data mining, and machine learning with some publications in these areas. Dr. Le also has experience in teaching courses in mathematics and statistics at several universities for both undergraduate and graduate levels.
- Applied Statistical Methods
- Data Analytics
- Healthcare Data Analytics
- Topics in Precalculus
Research and professional interests
- Bayesian analysis
- Data mining and machine learning
- Decision theory
- Model uncertainty and prediction
- Le, T. and Clarke, B., In praise of partially interpretable predictors. Statistical Analysis and Data Mining: The ASA Data Science Journal. Volume 13, 2020, Pages 113–133, DOI: https://doi.org/10.1002/sam.11450.
- Le, T. and Clarke, B., On the Interpretation of Ensemble Classifiers in terms of Bayes Classifiers. Journal of Classification, Volume 35, 2018, Pages 1–32, DOI: 10.1007/s00357-018-9257-y.
- Franz, T., Loecke, T., Burgin, A., Zhou, Y., Le, T., Moscicki, D., Spatio-temporal predictions of soil properties and states in variably saturated landscapes. Journal of Geophysical Research – Biogeosciences, Volume 122, 2017, Pages 1576–1596, DOI: 10.1002/2017JG003837.
- Le, T. and Clarke, B., A Bayes interpretation of stacking for M-complete and M-open settings. Bayesian Analysis, Volume 12, 2017, Pages 807–829, DOI: 10.1214/16-BA1023.
- Le, T. and Clarke, B., Using the Bayesian Shtarkov solution for predictions. Computational Statistics and Data Analysis, Volume 104, 2016, Pages 183–196, http://dx.doi.org/10.1016/j.csda.2016.06.018.
- Le, T. and Clarke, B., Model Averaging Is Asymptotically Better Than Model Selection For Prediction. Journal of Machine Learning Research. Volume 23, 2022, Pages 1-53, https://www.jmlr.org/papers/v23/20-874.html.
- Le, T. and Clarke, B., Interpreting uninterpretable predictors: kernel methods, Shtarkov solutions, and random forests. Statistical Theory and Related Fields. Volume 6, 2022, Pages 10-28, DOI: 10.1080/24754269.2021.1974157.
Contact Dr. Le
Office Location: 975 Blairs Bridge Rd, Lithia Springs, GA 30122, Suite 137K