The Computational Complexity of Sensitivity Analysis and Parameter Tuning
This provides foundational insights for researchers in computational complexity and AI, addressing whether recent achievements can be extended to more general methods, though it is incremental as it builds on existing complexity theory.
The paper established the computational complexity of sensitivity analysis and parameter tuning in probabilistic networks, showing that these problems are NPPP-complete in general and remain NP-complete or PP-complete for restricted variants.
While known algorithms for sensitivity analysis and parameter tuning in probabilistic networks have a running time that is exponential in the size of the network, the exact computational complexity of these problems has not been established as yet. In this paper we study several variants of the tuning problem and show that these problems are NPPP-complete in general. We further show that the problems remain NP-complete or PP-complete, for a number of restricted variants. These complexity results provide insight in whether or not recent achievements in sensitivity analysis and tuning can be extended to more general, practicable methods.