Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174991804> ?p ?o ?g. }
- W3174991804 abstract "We study the problem of estimating a rank-one matrix from Gaussian observations where different blocks of the matrix are observed under different noise levels. This problem is motivated by applications in clustering and community detection where latent variables can be partitioned into a fixed number of known groups (e.g., users and items) and the blocks of the matrix correspond to different types of pairwise interactions (e.g., user-user, user-item, or item-item interactions). In the setting where the number of blocks is fixed while the number of variables tends to infinity, we prove asymptotically exact formulas for the minimum mean-squared error in estimating both the matrix and the latent variables. These formulas describe the weak recovery thresholds for the problem and reveal invariance properties with respect to certain scalings of the noise variance. We also derive an approximate message passing algorithm and a gradient descent algorithm and show empirically that these algorithms achieve the information-theoretic limits in certain regimes." @default.
- W3174991804 created "2021-07-05" @default.
- W3174991804 creator A5074140720 @default.
- W3174991804 creator A5084396713 @default.
- W3174991804 date "2021-06-22" @default.
- W3174991804 modified "2023-09-27" @default.
- W3174991804 title "Rank-one matrix estimation with groupwise heteroskedasticity." @default.
- W3174991804 cites W1510028821 @default.
- W3174991804 cites W1520752838 @default.
- W3174991804 cites W1553702074 @default.
- W3174991804 cites W1975900269 @default.
- W3174991804 cites W2004531067 @default.
- W3174991804 cites W2066459155 @default.
- W3174991804 cites W2097714737 @default.
- W3174991804 cites W2097854052 @default.
- W3174991804 cites W2111616148 @default.
- W3174991804 cites W2129462326 @default.
- W3174991804 cites W2132657058 @default.
- W3174991804 cites W2138358551 @default.
- W3174991804 cites W2157638198 @default.
- W3174991804 cites W2159080219 @default.
- W3174991804 cites W2160752433 @default.
- W3174991804 cites W2169379894 @default.
- W3174991804 cites W2559839022 @default.
- W3174991804 cites W2588219153 @default.
- W3174991804 cites W2605304986 @default.
- W3174991804 cites W2793533891 @default.
- W3174991804 cites W2883384506 @default.
- W3174991804 cites W2898076323 @default.
- W3174991804 cites W2953102410 @default.
- W3174991804 cites W2963404710 @default.
- W3174991804 cites W2964213728 @default.
- W3174991804 cites W2964227601 @default.
- W3174991804 cites W2964282092 @default.
- W3174991804 cites W2992466427 @default.
- W3174991804 cites W3080456940 @default.
- W3174991804 cites W3095162319 @default.
- W3174991804 cites W3098822634 @default.
- W3174991804 cites W3098848552 @default.
- W3174991804 cites W3099176486 @default.
- W3174991804 cites W3099651934 @default.
- W3174991804 cites W3100129515 @default.
- W3174991804 cites W3101975788 @default.
- W3174991804 cites W3102974460 @default.
- W3174991804 cites W3103647971 @default.
- W3174991804 cites W3104504839 @default.
- W3174991804 cites W3104705273 @default.
- W3174991804 cites W3104859507 @default.
- W3174991804 cites W3105600170 @default.
- W3174991804 cites W3107979457 @default.
- W3174991804 cites W3126400887 @default.
- W3174991804 cites W3147353647 @default.
- W3174991804 cites W3155800910 @default.
- W3174991804 cites W3189983173 @default.
- W3174991804 cites W3005347330 @default.
- W3174991804 hasPublicationYear "2021" @default.
- W3174991804 type Work @default.
- W3174991804 sameAs 3174991804 @default.
- W3174991804 citedByCount "0" @default.
- W3174991804 crossrefType "posted-content" @default.
- W3174991804 hasAuthorship W3174991804A5074140720 @default.
- W3174991804 hasAuthorship W3174991804A5084396713 @default.
- W3174991804 hasConcept C101104100 @default.
- W3174991804 hasConcept C105795698 @default.
- W3174991804 hasConcept C106487976 @default.
- W3174991804 hasConcept C11413529 @default.
- W3174991804 hasConcept C114614502 @default.
- W3174991804 hasConcept C121332964 @default.
- W3174991804 hasConcept C159985019 @default.
- W3174991804 hasConcept C163716315 @default.
- W3174991804 hasConcept C164226766 @default.
- W3174991804 hasConcept C184898388 @default.
- W3174991804 hasConcept C192562407 @default.
- W3174991804 hasConcept C33923547 @default.
- W3174991804 hasConcept C62520636 @default.
- W3174991804 hasConcept C73555534 @default.
- W3174991804 hasConceptScore W3174991804C101104100 @default.
- W3174991804 hasConceptScore W3174991804C105795698 @default.
- W3174991804 hasConceptScore W3174991804C106487976 @default.
- W3174991804 hasConceptScore W3174991804C11413529 @default.
- W3174991804 hasConceptScore W3174991804C114614502 @default.
- W3174991804 hasConceptScore W3174991804C121332964 @default.
- W3174991804 hasConceptScore W3174991804C159985019 @default.
- W3174991804 hasConceptScore W3174991804C163716315 @default.
- W3174991804 hasConceptScore W3174991804C164226766 @default.
- W3174991804 hasConceptScore W3174991804C184898388 @default.
- W3174991804 hasConceptScore W3174991804C192562407 @default.
- W3174991804 hasConceptScore W3174991804C33923547 @default.
- W3174991804 hasConceptScore W3174991804C62520636 @default.
- W3174991804 hasConceptScore W3174991804C73555534 @default.
- W3174991804 hasLocation W31749918041 @default.
- W3174991804 hasOpenAccess W3174991804 @default.
- W3174991804 hasPrimaryLocation W31749918041 @default.
- W3174991804 hasRelatedWork W1516765225 @default.
- W3174991804 hasRelatedWork W2040482074 @default.
- W3174991804 hasRelatedWork W2045018165 @default.
- W3174991804 hasRelatedWork W2052077920 @default.
- W3174991804 hasRelatedWork W2159416808 @default.
- W3174991804 hasRelatedWork W2509232189 @default.
- W3174991804 hasRelatedWork W2512248760 @default.