Department of Mechanical and Aerospace Engineering

Daniel Tartakovsky › Publications › boso-2020-learning

F. Boso and D. M. Tartakovsky, "Learning on dynamic statistical manifolds", *Proc. Roy. Soc. A*, vol. 476, no. 2239, doi:10.1098/rspa.2020.0213, pp. 20200213, 2020

Hyperbolic balance laws with uncertain (random) parameters and inputs are ubiquitous in science and engineering. Quantification of uncertainty in predictions derived from such laws, and reduction of predictive uncertainty via data assimilation, remain an open challenge. That is due to nonlinearity of governing equations, whose solutions are highly non-Gaussian and often discontinuous. To ameliorate these issues in a computationally efficient way, we use the method of distributions, which here takes the form of a deterministic equation for spatiotemporal evolution of the cumulative distribution function (CDF) of the random system state, as a means of forward uncertainty propagation. Uncertainty reduction is achieved by recasting the standard loss function, i.e., discrepancy between observations and model predictions, in distributional terms. This step exploits the equivalence between minimization of the square error discrepancy and the Kullback-Leibler divergence. The loss function is regularized by adding a Lagrangian constraint enforcing fulfillment of the CDF equation. Minimization is performed sequentially, progressively updating the parameters of the CDF equation as more measurements are assimilated.

@article{boso-2020-learning,

author = {F. Boso and D. M. Tartakovsky},

title = {Learning on dynamic statistical manifolds},

year = {2020},

urlpdf = {http://maeresearch.ucsd.edu/Tartakovsky/Papers/boso-2020-learning.pdf},

journal = {Proc. Roy. Soc. A},

volume = {476},

number = {2239},

doi = {10.1098/rspa.2020.0213},

pages = {20200213}

}