• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Computing Divergences between Discrete Decomposable Models
 
  • Details
  • Full
Options
June 26, 2023
Conference Paper
Title

Computing Divergences between Discrete Decomposable Models

Abstract
There are many applications that benefit from computing the exact divergence between 2 discrete probability measures, including machine learning. Unfortunately, in the absence of any assumptions on the structure or independencies within these distributions, computing the divergence between them is an intractable problem in high dimensions. We show that we are able to compute a wide family of functionals and divergences, such as the alpha-beta divergence, between two decomposable models, i.e. chordal Markov networks, in time exponential to the treewidth of these models. The alpha-beta divergence is a family of divergences that include popular divergences such as the Kullback-Leibler divergence, the Hellinger distance, and the chi-squared divergence. Thus, we can accurately compute the exact values of any of this broad class of divergences to the extent to which we can accurately model the two distributions using decomposable models.
Author(s)
Lee, Loong Kuan
Monash University, Department of Data Science and AI
Piatkowski, Nico  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Petitjean, François
Monash University, Department of Data Science and AI
Webb, Geoffrey
Monash University, Department of Data Science and AI
Mainwork
Thirty-Seventh AAAI Conference on Artificial Intelligence 2023. Proceedings. No.10: AAAI-23 Technical Tracks 10  
Conference
Conference on Artificial Intelligence 2023  
Conference on Innovative Applications of Artificial Intelligence 2023  
Symposium on Educational Advances in Artificial Intelligence 2023  
Open Access
DOI
10.1609/aaai.v37i10.26443
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Keyword(s)
  • Graphical Model

  • Stochastic Models

  • Probabilistic Inference

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024