Convergence of best phi -entropy estimates

M. Teboulle, I. Vajda

Research output: Contribution to journalArticlepeer-review

Abstract

Minimization problems involving phi -entropy functionals (a generalization of Boltzmann-Shannon entropy) are studied over a given set A and a sequence of sets A/sub n/ and the properties of their optimal solutions x/sub phi /, x/sub n/. Under certain conditions on the objective functional and the sets A and A/sub n/, it is proven that as n increases to infinity, the optimal solution x/sub n/ converges in L/sub 1/ norm to the test phi -entropy estimate x/sub phi /.
Original languageUndefined/Unknown
Pages (from-to)297-301
Number of pages5
JournalIEEE Transactions on Information Theory
Volume39
Issue number1
DOIs
StatePublished - 1 Jan 1993

Keywords

  • Entropy functionals
  • convex optimization
  • maximum entropy methods
  • norm convergence
  • set-convergence

Cite this