Loading...
research article
Generalized maximum entropy estimation
January 1, 2019
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.
Use this identifier to reference this record
Type
research article
Web of Science ID
WOS:000491132200002
Authors
Publication date
2019-01-01
Published in
Volume
20
Start page
138
Peer reviewed
REVIEWED
EPFL units
Available on Infoscience
October 31, 2019