Rebecca Elizabeth Morrison

UQ Group, Department of Aeronautics and Astronautics
Massachusetts Institute of Technology

office: 37-431
email: rmorriso AT

PhD in Computational Science, Engineering, and Mathematics, UT Austin, 2016

Research Interests

Designing data-driven models that respect physical constraints/information
Probabilistic graphical models and sparsity of Markov random fields
Mathematical representations of model inadequacy
High-dimensional Bayesian modeling and model inversion
Calibration, validation, and uncertainty quantification for predictive models

Publications & Reports

  1. R. E. Morrison, R. D. Moser, T. A. Oliver. Representing model inadequacy: A stochastic operator approach. To appear in SIAM Journal of Uncertainty Quantification. Arxiv.

  2. R. E. Morrison, R. Baptista, Y. Marzouk. Beyond normality: Learning sparse probabilistic graphical models in the non-Gaussian setting. NIPS 2017.

  3. R. E. Morrison. On the representation of model inadequacy: A stochastic operator approach. Dissertation in Computational Science, Engineering, and Mathematics. ICES, UT Austin, January 2016.

  4. R. E. Morrison, C. M. Bryant, G. Terejanu, S. Prudhomme, K. Miki. Data partition methodology for validation of predictive models. Computers and Mathematics with Applications 66 (10) 2114-2125; 2013. Arxiv.

  5. R. E. Morrison, C. Bryant, G. Terejanu, K. Miki, S. Prudhomme. Optimal data split methodology for model validation. In proceedings of and presented at the World Congress on Engineering and Computer Science. San Francisco, CA, October 2011.

  6. R. E. Morrison, A. S. Landsberg, E. J. Friedman. Combinatorial Games with a Pass: A dynamical systems approach. Chaos 21, 043108; 2011. Arxiv.

Curriculum Vitae