Decision-Centric Uncertainty Propagation

This work is concerned with providing a better approximation to the probability density function by incorporating contextual loss information, here a region of interest in state space, held by the decision maker into the uncertainty propagation process. Due to the approximations used in propagating the conditional probability density function it may happen that no or very little probability density mass exists in the region of interest at the decision time. Thus the expected risk will be significantly underestimated, misguiding this way the decision maker. We propose a non-intrusive method in computing an approximate probability density function that addresses the region of interest and it is closer to the true probability density function.

  • G. Terejanu, P. Singla, T. Singh, and P. D. Scott, “A Decision-Centric Framework for Density Forecasting,” Journal of Advances in Information Fusion, vol. 5, iss. 2, pp. 73-87, 2010.
    [BibTeX]
    @ARTICLE{TerejanuJ_JAIF_2010,
    author = {Gabriel Terejanu and Puneet Singla and Tarunraj Singh and Peter D. Scott},
    title = {{A Decision-Centric Framework for Density Forecasting}},
    journal = {{Journal of Advances in Information Fusion}},
    volume = {5},
    number = {2},
    pages = {73-87},
    year = {2010},
    month = {Dec.},
    }

  • G. Terejanu, P. Singla, T. Singh, and P. D. Scott, “Decision Based Uncertainty Propagation Using Adaptive Gaussian Mixtures,” in 12th International Conference on Information Fusion, Seattle, Washington, 2009.
    [BibTeX]
    @CONFERENCE{TerejanuP_IF_2009,
    author = {Gabriel Terejanu and Puneet Singla and Tarunraj Singh and Peter D. Scott},
    title = {{Decision Based Uncertainty Propagation Using Adaptive Gaussian Mixtures}},
    booktitle = {{12th International Conference on Information Fusion, Seattle, Washington}},
    year = {2009},
    month = {July},
    }