Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964137601> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2964137601 endingPage "775" @default.
- W2964137601 startingPage "767" @default.
- W2964137601 abstract "In this paper, we study the information-theoretic limits of learning the structure of Bayesian networks (BNs), on discrete as well as continuous random variables, from a finite number of samples. We show that the minimum number of samples required by any procedure to recover the correct structure grows as $Omega(m)$ and $Omega(k log m + (k^2/m))$ for non-sparse and sparse BNs respectively, where $m$ is the number of variables and $k$ is the maximum number of parents per node. We provide a simple recipe, based on an extension of the Fano's inequality, to obtain information-theoretic limits of structure recovery for any exponential family BN. We instantiate our result for specific conditional distributions in the exponential family to characterize the fundamental limits of learning various commonly used BNs, such as conditional probability table based networks, gaussian BNs, noisy-OR networks, and logistic regression networks. En route to obtaining our main results, we obtain tight bounds on the number of sparse and non-sparse essential-DAGs. Finally, as a byproduct, we recover the information-theoretic limits of sparse variable selection for logistic regression." @default.
- W2964137601 created "2019-07-30" @default.
- W2964137601 creator A5021080594 @default.
- W2964137601 creator A5038965118 @default.
- W2964137601 date "2017-04-10" @default.
- W2964137601 modified "2023-09-26" @default.
- W2964137601 title "Information-theoretic limits of Bayesian network structure learning" @default.
- W2964137601 hasPublicationYear "2017" @default.
- W2964137601 type Work @default.
- W2964137601 sameAs 2964137601 @default.
- W2964137601 citedByCount "9" @default.
- W2964137601 countsByYear W29641376012017 @default.
- W2964137601 countsByYear W29641376012018 @default.
- W2964137601 countsByYear W29641376012019 @default.
- W2964137601 countsByYear W29641376012020 @default.
- W2964137601 crossrefType "proceedings-article" @default.
- W2964137601 hasAuthorship W2964137601A5021080594 @default.
- W2964137601 hasAuthorship W2964137601A5038965118 @default.
- W2964137601 hasConcept C105795698 @default.
- W2964137601 hasConcept C121332964 @default.
- W2964137601 hasConcept C122123141 @default.
- W2964137601 hasConcept C134306372 @default.
- W2964137601 hasConcept C151201525 @default.
- W2964137601 hasConcept C154945302 @default.
- W2964137601 hasConcept C163716315 @default.
- W2964137601 hasConcept C174920663 @default.
- W2964137601 hasConcept C28826006 @default.
- W2964137601 hasConcept C33724603 @default.
- W2964137601 hasConcept C33923547 @default.
- W2964137601 hasConcept C41008148 @default.
- W2964137601 hasConcept C55974624 @default.
- W2964137601 hasConcept C62520636 @default.
- W2964137601 hasConceptScore W2964137601C105795698 @default.
- W2964137601 hasConceptScore W2964137601C121332964 @default.
- W2964137601 hasConceptScore W2964137601C122123141 @default.
- W2964137601 hasConceptScore W2964137601C134306372 @default.
- W2964137601 hasConceptScore W2964137601C151201525 @default.
- W2964137601 hasConceptScore W2964137601C154945302 @default.
- W2964137601 hasConceptScore W2964137601C163716315 @default.
- W2964137601 hasConceptScore W2964137601C174920663 @default.
- W2964137601 hasConceptScore W2964137601C28826006 @default.
- W2964137601 hasConceptScore W2964137601C33724603 @default.
- W2964137601 hasConceptScore W2964137601C33923547 @default.
- W2964137601 hasConceptScore W2964137601C41008148 @default.
- W2964137601 hasConceptScore W2964137601C55974624 @default.
- W2964137601 hasConceptScore W2964137601C62520636 @default.
- W2964137601 hasLocation W29641376011 @default.
- W2964137601 hasOpenAccess W2964137601 @default.
- W2964137601 hasPrimaryLocation W29641376011 @default.
- W2964137601 hasRelatedWork W1524326598 @default.
- W2964137601 hasRelatedWork W2021368287 @default.
- W2964137601 hasRelatedWork W2038224551 @default.
- W2964137601 hasRelatedWork W2109605413 @default.
- W2964137601 hasRelatedWork W2147071755 @default.
- W2964137601 hasRelatedWork W2200666419 @default.
- W2964137601 hasRelatedWork W2381572595 @default.
- W2964137601 hasRelatedWork W2395418183 @default.
- W2964137601 hasRelatedWork W2530136521 @default.
- W2964137601 hasRelatedWork W2549402093 @default.
- W2964137601 hasRelatedWork W2560985450 @default.
- W2964137601 hasRelatedWork W2751177214 @default.
- W2964137601 hasRelatedWork W2800859579 @default.
- W2964137601 hasRelatedWork W2951124571 @default.
- W2964137601 hasRelatedWork W2963266994 @default.
- W2964137601 hasRelatedWork W2971301274 @default.
- W2964137601 hasRelatedWork W3191860072 @default.
- W2964137601 hasRelatedWork W323443579 @default.
- W2964137601 hasRelatedWork W2162811297 @default.
- W2964137601 hasRelatedWork W3121098844 @default.
- W2964137601 isParatext "false" @default.
- W2964137601 isRetracted "false" @default.
- W2964137601 magId "2964137601" @default.
- W2964137601 workType "article" @default.