Belief Propagation: Accurate Marginals or Accurate Partition Function - Where is the Difference?

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem Konferenzband

Abstract

We analyze belief propagation on patch potential models -- these are attractive models with varying local potentials -- obtain all of the possibly many fixed points, and gather novel insights into belief propagation's properties. In particular, we observe and theoretically explain several regions in the parameter space that behave fundamentally different. We specify and elaborate on one specific region that, despite the existence of multiple fixed points, is relatively well behaved and provides insights into the relationship between the accuracy of the marginals and the partition function. We demonstrate the inexistence of a principle relationship between both quantities and provide sufficient conditions for a fixed point to be optimal with respect to approximating both the marginals and the partition function.
Originalspracheenglisch
TitelUncertainty in Artificial Intelligence
PublikationsstatusVeröffentlicht - 23 Jul 2019
Veranstaltung2019 Conference on Uncertainty in Artificial Intelligence - Tel Aviv, Israel
Dauer: 22 Jul 201925 Jul 2019

Konferenz

Konferenz2019 Conference on Uncertainty in Artificial Intelligence
KurztitelUAI 2019
LandIsrael
OrtTel Aviv
Zeitraum22/07/1925/07/19

Fingerprint Untersuchen Sie die Forschungsthemen von „Belief Propagation: Accurate Marginals or Accurate Partition Function - Where is the Difference?“. Zusammen bilden sie einen einzigartigen Fingerprint.

  • Verwandte Tätigkeiten

    • 1 Vortrag bei Konferenz oder Fachtagung

    Belief Propagation: Accurate Marginals or Accurate Partition Function -- Where is the Difference?

    Christian Knoll (Redner/in)
    23 Jul 2019

    Aktivität: Vortrag oder PräsentationVortrag bei Konferenz oder FachtagungScience to science

    Dieses zitieren