Matches in SemOpenAlex for { <https://semopenalex.org/work/W2770109286> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2770109286 abstract "We propose an efficient meta-algorithm for Bayesian inference problems based on low-degree polynomials, semidefinite programming, and tensor decomposition. The algorithm is inspired by recent lower bound constructions for sum-of-squares and related to the method of moments. Our focus is on sample complexity bounds that are as tight as possible (up to additive lower-order terms) and often achieve statistical thresholds or conjectured computational thresholds. Our algorithm recovers the best known bounds for partial recovery in the stochastic block model, a widely-studied class of inference problems for community detection in graphs. We obtain the first partial recovery guarantees for the mixed-membership stochastic block model (Airoldi et el.) for constant average degree-up to what we conjecture to be the computational threshold for this model. We show that our algorithm exhibits a sharp computational threshold for the stochastic block model with multiple communities beyond the Kesten-Stigum bound-giving evidence that this task may require exponential time. The basic strategy of our algorithm is strikingly simple: we compute the best-possible low-degree approximation for the moments of the posterior distribution of the parameters and use a robust tensor decomposition algorithm to recover the parameters from these approximate posterior moments." @default.
- W2770109286 created "2017-12-04" @default.
- W2770109286 creator A5001123654 @default.
- W2770109286 creator A5089128021 @default.
- W2770109286 date "2017-10-01" @default.
- W2770109286 modified "2023-10-16" @default.
- W2770109286 title "Efficient Bayesian Estimation from Few Samples: Community Detection and Related Problems" @default.
- W2770109286 cites W2014565165 @default.
- W2770109286 cites W2022749269 @default.
- W2770109286 cites W2023348178 @default.
- W2770109286 cites W2033154334 @default.
- W2770109286 cites W2057214765 @default.
- W2770109286 cites W2080207853 @default.
- W2770109286 cites W2093663313 @default.
- W2770109286 cites W2219655028 @default.
- W2770109286 cites W2296148711 @default.
- W2770109286 cites W2962721953 @default.
- W2770109286 cites W2962907923 @default.
- W2770109286 cites W2963256102 @default.
- W2770109286 doi "https://doi.org/10.1109/focs.2017.42" @default.
- W2770109286 hasPublicationYear "2017" @default.
- W2770109286 type Work @default.
- W2770109286 sameAs 2770109286 @default.
- W2770109286 citedByCount "61" @default.
- W2770109286 countsByYear W27701092862018 @default.
- W2770109286 countsByYear W27701092862019 @default.
- W2770109286 countsByYear W27701092862020 @default.
- W2770109286 countsByYear W27701092862021 @default.
- W2770109286 countsByYear W27701092862022 @default.
- W2770109286 countsByYear W27701092862023 @default.
- W2770109286 crossrefType "proceedings-article" @default.
- W2770109286 hasAuthorship W2770109286A5001123654 @default.
- W2770109286 hasAuthorship W2770109286A5089128021 @default.
- W2770109286 hasConcept C101901036 @default.
- W2770109286 hasConcept C105795698 @default.
- W2770109286 hasConcept C11413529 @default.
- W2770109286 hasConcept C121332964 @default.
- W2770109286 hasConcept C126255220 @default.
- W2770109286 hasConcept C134306372 @default.
- W2770109286 hasConcept C148764684 @default.
- W2770109286 hasConcept C179799912 @default.
- W2770109286 hasConcept C24890656 @default.
- W2770109286 hasConcept C2775997480 @default.
- W2770109286 hasConcept C2779982251 @default.
- W2770109286 hasConcept C33923547 @default.
- W2770109286 hasConcept C73555534 @default.
- W2770109286 hasConcept C77553402 @default.
- W2770109286 hasConceptScore W2770109286C101901036 @default.
- W2770109286 hasConceptScore W2770109286C105795698 @default.
- W2770109286 hasConceptScore W2770109286C11413529 @default.
- W2770109286 hasConceptScore W2770109286C121332964 @default.
- W2770109286 hasConceptScore W2770109286C126255220 @default.
- W2770109286 hasConceptScore W2770109286C134306372 @default.
- W2770109286 hasConceptScore W2770109286C148764684 @default.
- W2770109286 hasConceptScore W2770109286C179799912 @default.
- W2770109286 hasConceptScore W2770109286C24890656 @default.
- W2770109286 hasConceptScore W2770109286C2775997480 @default.
- W2770109286 hasConceptScore W2770109286C2779982251 @default.
- W2770109286 hasConceptScore W2770109286C33923547 @default.
- W2770109286 hasConceptScore W2770109286C73555534 @default.
- W2770109286 hasConceptScore W2770109286C77553402 @default.
- W2770109286 hasLocation W27701092861 @default.
- W2770109286 hasOpenAccess W2770109286 @default.
- W2770109286 hasPrimaryLocation W27701092861 @default.
- W2770109286 hasRelatedWork W2288310039 @default.
- W2770109286 hasRelatedWork W2938809110 @default.
- W2770109286 hasRelatedWork W2963545258 @default.
- W2770109286 hasRelatedWork W2963988651 @default.
- W2770109286 hasRelatedWork W3127919261 @default.
- W2770109286 hasRelatedWork W3158298591 @default.
- W2770109286 hasRelatedWork W3204565202 @default.
- W2770109286 hasRelatedWork W4287184521 @default.
- W2770109286 hasRelatedWork W4287332923 @default.
- W2770109286 hasRelatedWork W4301912994 @default.
- W2770109286 isParatext "false" @default.
- W2770109286 isRetracted "false" @default.
- W2770109286 magId "2770109286" @default.
- W2770109286 workType "article" @default.