Minimax robust decentralized detection
Venugopal V. Veeravalli, Tamer Başar, H. Vincent Poor · IEEE Transactions on Information Theory · 1994
Decentralized detection problems are studied where the sensor distributions are not specified completely. The sensor distributions are assumed to belong to known uncertainty classes. It is shown for a broad class of such problems that a set of least favorable distributions exists for minimax robust testing between the hypotheses. It is hence established that the corresponding minimax robust tests are solutions to simple decentralized detection problems for which the sensor distributions are specified to be the least favorable distributions.>