TY - GEN
T1 - Robustness via a tradeoff between fisher information and relative entropy
AU - Li, Lichun
AU - O'Sullivan, Joseph A.
PY - 2007
Y1 - 2007
N2 - We look at the problem of finding the worst-case distribution in a convex family of distributions defined as those whose relative entropy, relative to a nominal distribution, is less than a threshold. The worst-case distribution is selected as the one whose Fisher information for the mean of the distribution is the lowest. This problem is connected to a penalized maximum likelihood estimation problem. We present a novel algorithm for computing this worst-case (robust) distribution, show implementation results and analyze properties of the robust distribution.
AB - We look at the problem of finding the worst-case distribution in a convex family of distributions defined as those whose relative entropy, relative to a nominal distribution, is less than a threshold. The worst-case distribution is selected as the one whose Fisher information for the mean of the distribution is the lowest. This problem is connected to a penalized maximum likelihood estimation problem. We present a novel algorithm for computing this worst-case (robust) distribution, show implementation results and analyze properties of the robust distribution.
KW - Fisher information
KW - Maximum likelihood estimation
KW - Optimization
KW - Relative entropy
KW - Robustness
UR - https://www.scopus.com/pages/publications/47849126631
U2 - 10.1109/SSP.2007.4301255
DO - 10.1109/SSP.2007.4301255
M3 - Conference contribution
AN - SCOPUS:47849126631
SN - 142441198X
SN - 9781424411986
T3 - IEEE Workshop on Statistical Signal Processing Proceedings
SP - 239
EP - 243
BT - 2007 IEEE/SP 14th Workshop on Statistical Signal Processing, SSP 2007, Proceedings
T2 - 2007 IEEE/SP 14th WorkShoP on Statistical Signal Processing, SSP 2007
Y2 - 26 August 2007 through 29 August 2007
ER -