Generalized maximum entropy estimation

Tobias Sutter, David Sutter, Peyman Mohajerin Esfahani, John Lygeros

Research output: Contribution to journalArticleScientificpeer-review

1 Citation (Scopus)
18 Downloads (Pure)

Abstract

We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise. Based on duality of convex programming, we present a novel approximation scheme using a smoothed fast gradient method that is equipped with explicit bounds on the approximation error. We further demonstrate how the presented scheme can be used for approximating the chemical master equation through the zero-information moment closure method, and for an approximate dynamic programming approach in the context of constrained Markov decision processes with uncountable state and action spaces.

Original languageEnglish
Number of pages29
JournalJournal of Machine Learning Research
Volume20
Issue number138
Publication statusPublished - 2019

Keywords

  • Approximate dynamic programming
  • Convex optimization
  • Entropy maximization
  • Fast gradient method
  • Relative entropy minimization

Fingerprint Dive into the research topics of 'Generalized maximum entropy estimation'. Together they form a unique fingerprint.

Cite this