TY - GEN
T1 - Strong large deviations for composite hypothesis testing
AU - Huang, Yen Wei
AU - Moulin, Pierre
PY - 2014
Y1 - 2014
N2 - A simple hypothesis P is tested against a composite hypothesis Q j, j ∈ [1,2,⋯,k], each Qj being a product of n probability distributions. We consider the set of achievable false-positive error probability vectors for a generalized Neyman-Pearson test under a constraint on the probability of correct detection under P. Exact asymptotics (as n → ∞) are derived for this set, in particular the set is determined within an O(1) term.
AB - A simple hypothesis P is tested against a composite hypothesis Q j, j ∈ [1,2,⋯,k], each Qj being a product of n probability distributions. We consider the set of achievable false-positive error probability vectors for a generalized Neyman-Pearson test under a constraint on the probability of correct detection under P. Exact asymptotics (as n → ∞) are derived for this set, in particular the set is determined within an O(1) term.
UR - http://www.scopus.com/inward/record.url?scp=84906547941&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84906547941&partnerID=8YFLogxK
U2 - 10.1109/ISIT.2014.6874894
DO - 10.1109/ISIT.2014.6874894
M3 - Conference contribution
AN - SCOPUS:84906547941
SN - 9781479951864
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 556
EP - 560
BT - 2014 IEEE International Symposium on Information Theory, ISIT 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Symposium on Information Theory, ISIT 2014
Y2 - 29 June 2014 through 4 July 2014
ER -