Complexity of Solving Decision Trees with Skew-Symmetric Bilinear Utility - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Complexity of Solving Decision Trees with Skew-Symmetric Bilinear Utility

Hugo Gilbert
Olivier Spanjaard

Abstract

We study the complexity of solving decision trees with a Skew-Symmetric Bilinear (SSB) utility function. The SSB model is an extension of Expected Utility (EU) with enhanced descriptive possibilities. Unlike EU, the opti-mality principle does not hold for SSB, which makes its optimization trickier. We show that determining an SSB optimal plan is NP-hard if one only considers deterministic plans while it is polynomial time if one allows randomized plans. With the Weighted EU model (a special case of SSB), the problem becomes polynomial in both settings. Our numerical tests show the operationality of the methods.
Fichier principal
Vignette du fichier
hgos.pdf (311.86 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01562272 , version 1 (13-07-2017)

Identifiers

  • HAL Id : hal-01562272 , version 1

Cite

Hugo Gilbert, Olivier Spanjaard. Complexity of Solving Decision Trees with Skew-Symmetric Bilinear Utility. Conference on Uncertainty in Artificial Intelligence (UAI-2017), Aug 2017, Sydney, Australia. ⟨hal-01562272⟩
93 View
119 Download

Share

Gmail Facebook X LinkedIn More