Skip to main content
added 113 characters in body
Source Link
Steve Huntsman
  • 15.4k
  • 7
  • 75
  • 130

The relative entropy is frequently framed as the inverse temperature times the difference between the Helmholtz and variational/Bethe free energies, the latter of which is minimized as a proxy objective function in mean field theory and Bayesian estimation via the well-known expectation maximization algorithm. MacKay's book is a good reference for this.

The relative entropy is frequently framed as the inverse temperature times the difference between the Helmholtz and variational/Bethe free energies, the latter of which is minimized as a proxy objective function in mean field theory and Bayesian estimation via the well-known expectation maximization algorithm.

The relative entropy is frequently framed as the inverse temperature times the difference between the Helmholtz and variational/Bethe free energies, the latter of which is minimized as a proxy objective function in mean field theory and Bayesian estimation via the well-known expectation maximization algorithm. MacKay's book is a good reference for this.

Source Link
Steve Huntsman
  • 15.4k
  • 7
  • 75
  • 130

The relative entropy is frequently framed as the inverse temperature times the difference between the Helmholtz and variational/Bethe free energies, the latter of which is minimized as a proxy objective function in mean field theory and Bayesian estimation via the well-known expectation maximization algorithm.