Tradeoffs in Constructing and Evaluating Temporal Influence Diagrams
This work addresses tradeoffs in probabilistic reasoning for dynamic systems, but it appears incremental as it builds on existing TID frameworks without introducing a new paradigm.
The paper tackles the problem of constructing and evaluating Temporal Influence Diagrams (TIDs) to model dynamic systems without excessive data or computational costs, by examining three approaches that make different tradeoffs and proposing methods to evaluate their accuracy and efficiency.
This paper addresses the tradeoffs which need to be considered in reasoning using probabilistic network representations, such as Influence Diagrams (IDs). In particular, we examine the tradeoffs entailed in using Temporal Influence Diagrams (TIDs) which adequately capture the temporal evolution of a dynamic system without prohibitive data and computational requirements. Three approaches for TID construction which make different tradeoffs are examined: (1) tailoring the network at each time interval to the data available (rather then just copying the original Bayes Network for all time intervals); (2) modeling the evolution of a parsimonious subset of variables (rather than all variables); and (3) model selection approaches, which seek to minimize some measure of the predictive accuracy of the model without introducing too many parameters, which might cause "overfitting" of the model. Methods of evaluating the accuracy/efficiency of the tradeoffs are proposed.