Abstract | ||
---|---|---|
This paper proposes a formal definition of influence in Bayesian reasoning, based on the notions of state (as probability distribution), predicate, validity and conditioning. Our approach highlights how conditioning a joint entwined/entangled state with a predicate on one of its components has u0027crossoveru0027 influence on the other components. We use the total variation metric on probabilitydistributions to quantitatively measure such influence. These insights are applied to give a rigorous explanation of the fundamental concept of d-separation in Bayesian networks. |
Year | Venue | Field |
---|---|---|
2017 | MFCS | Discrete mathematics,Crossover,Bayesian inference,Computer science,Formal description,Theoretical computer science,Probability distribution,Bayesian network,Predicate (grammar),Semantics of logic |
DocType | Citations | PageRank |
Conference | 1 | 0.38 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
B. Jacobs | 1 | 1046 | 100.09 |
Fabio Zanasi | 2 | 110 | 13.89 |