strong lap condition
Distributed Parameter Estimation in Probabilistic Graphical Models
Yariv D. Mizrahi, Misha Denil, Nando None de Freitas
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimators are consistent.
Distributed Parameter Estimation in Probabilistic Graphical Models University of British Columbia, Canada University of Oxford, United Kingdom
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimators are consistent.
Distributed Parameter Estimation in Probabilistic Graphical Models
Mizrahi, Yariv D., Denil, Misha, Freitas, Nando de
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimators are consistent.
Distributed Parameter Estimation in Probabilistic Graphical Models
Mizrahi, Yariv Dror, Denil, Misha, de Freitas, Nando
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimators are consistent.