Formulation and properties of a divergence used to compare probability measures without absolute continuity
Abstract
This paper develops a new divergence that generalizes relative entropy and can be used to compare probability measures without a requirement of absolute continuity. We establish properties of the divergence, and in particular derive and exploit a representation as an infimum convolution of optimal transport cost and relative entropy. Also included are examples of computation and approximation of the divergence, and the demonstration of properties that are useful when one quantifies model uncertainty.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jan 01, 2022
- Source ID
- 10.1051/cocv/2022002
Entities
People
- Paul Dupuis
- Yixiang Mao
Organizations
- Air Force Office of Scientific Research
- National Science Foundation Directorate for Mathematical & Physical Sciences