Extremum Problems With Total Variation Distance and Their Applications

DOI10.1109/TAC.2014.2321951MaRDI QIDQ2983022zbMATH OpenOpenAlexFDO

Authors I. Tzortzis, Sergey Loyka, Themistoklis Charalambous, Charalambos D. Charalambous

Publication date 16 May 2017

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1301.4763

Mathematics Subject Classification ID

Probability measures on topological spaces (60B05) Optimality conditions for problems involving randomness (49K45)

Abstract: The aim of this paper is to investigate extremum problems with pay-off being the total variational distance metric defined on the space of probability measures, subject to linear functional constraints on the space of probability measures, and vice-versa; that is, with the roles of total variational metric and linear functional interchanged. Utilizing concepts from signed measures, the extremum probability measures of such problems are obtained in closed form, by identifying the partition of the support set and the mass of these extremum measures on the partition. The results are derived for abstract spaces; specifically, complete separable metric spaces known as Polish spaces, while the high level ideas are also discussed for denumerable spaces endowed with the discrete topology. These extremum problems often arise in many areas, such as, approximating a family of probability distributions by a given probability distribution, maximizing or minimizing entropy subject to total variational distance metric constraints, quantifying uncertainty of probability distributions by total variational distance metric, stochastic minimax control, and in many problems of information, decision theory, and minimax theory.

Recommendations

• Extremal problems for close-to-convex functions
• Extremal problems related to convexity
• Extremal problems for extremal distance and harmonic measure
• On the extremum problems with constraints in the metric space
• Extremal problems under dimension constraints.
• Extremal problems dual to the Gauss variational problem
• Extremal problems and related Dirichlet problems
• scientific article; zbMATH DE number 3925825
• scientific article; zbMATH DE number 92455
• scientific article; zbMATH DE number 3625110

Cited in

(8)

• Infinite Horizon Average Cost Dynamic Programming Subject to Total Variation Distance Ambiguity
• Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learning
• The pure exploration problem with general reward functions depending on full distributions
• The average cost of Markov chains subject to total variation distance uncertainty
• Dynamic programming subject to total variation distance ambiguity
• Isometries of probability measures with respect to the total variation distance
• scientific article; zbMATH DE number 3949178 (Why is no real title available?)
• scientific article; zbMATH DE number 7632135 (Why is no real title available?)

This page was built for publication: Extremum Problems With Total Variation Distance and Their Applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2983022)