Browsing by Subject "Sufficient conditions"
Now showing items 1-6 of 6
-
Conference Object
Bound on the probability of HMM misclassification
(2011)In this paper we consider the problem of classifying a sequence of observations among two known hidden Markov models (HMMs). We use a classifier that minimizes the probability of error (i.e., the probability of misclassification), ...
-
Conference Object
Convergence of belief propagation algorithms on binary pairwise Gibbs random fields
(2011)In this paper, we study the convergence of belief propagation algorithms (BPAs) on binary pairwise Gibbs random fields (BP-GRFs). Exploiting the equivalence of BPA on the graph associated with BP-GRF and the corresponding ...
-
Article
Decentralized optimality conditions of stochastic differential decision problems via Girsanov’s measure transformation
(2016)In this paper, we apply two methods to derive necessary and sufficient decentralized optimality conditions for stochastic differential decision problems with multiple Decision Makers (DMs), which aim at optimizing a common ...
-
Conference Object
A general framework for continuous time power control in time varying long term fading wireless networks
(2007)In this paper, a general framework for continuous time power control algorithm under time varying long term fading wireless channels is developed. This contrasts most of the power control algorithms introduced in the ...
-
Article
LQG optimality and separation principle for general discrete time partially observed stochastic systems over finite capacity communication channels
(2008)This paper is concerned with control of stochastic systems subject to finite communication channel capacity. Necessary conditions for reconstruction and stability of system outputs are derived using the Information ...
-
Conference Object
Probability of error bounds for failure diagnosis and classification in hidden Markov models
(2008)In this paper we consider a formulation of the failure diagnosis problem in stochastic systems as a maximum likelihood classification problem: a diagnoser observes the system under diagnosis online and determines which ...