Jm. Borwein et al., MAXIMUM-ENTROPY RECONSTRUCTION USING DERIVATIVE INFORMATION .1. FISHER INFORMATION AND CONVEX DUALITY, Mathematics of operations research, 21(2), 1996, pp. 442-468
Citations number
36
Categorie Soggetti
Operatione Research & Management Science",Mathematics,"Operatione Research & Management Science",Mathematics
Maximum entropy spectral density estimation is a technique for reconst
ructing an unknown density function from some known measurements by ma
ximizing a given measure of entropy of the estimate. Here we present a
variety of new entropy measures which attempt to control derivative v
alues of the densities. Our models apply among others to the inference
problem based on the averaged Fisher information measure. The duality
theory we develop resembles models used in convex optimal control pro
blems. We present a variety of examples, including relaxed moment matc
hing with Fisher information and best interpolation on a strip.