FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2510191442> ?p ?o ?g. }

• W2510191442 abstract "The quality of K-Means clustering is extremely sensitive to proper initialization. The classic remedy is to apply k-means++ to obtain an initial set of centers that is provably competitive with the optimal solution. Unfortunately, k-means++ requires k full passes over the data which limits its applicability to massive datasets. We address this problem by proposing a simple and efficient seeding algorithm for K-Means clustering. The main idea is to replace the exact D2-sampling step in k-means++ with a substantially faster approximation based on Markov Chain Monte Carlo sampling. We prove that, under natural assumptions on the data, the proposed algorithm retains the full theoretical guarantees of k-means++ while its computational complexity is only sublinear in the number of data points. For such datasets, one can thus obtain a provably good clustering in sublinear time. Extensive experiments confirm that the proposed method is competitive with k-means++ on a variety of real-world, large-scale datasets while offering a reduction in runtime of several orders of magnitude." @default.
• W2510191442 created "2016-09-16" @default.
• W2510191442 creator A5003040843 @default.
• W2510191442 creator A5044677020 @default.
• W2510191442 creator A5078613749 @default.
• W2510191442 creator A5089890773 @default.
• W2510191442 date "2016-02-21" @default.
• W2510191442 modified "2023-10-15" @default.
• W2510191442 title "Approximate K-Means++ in Sublinear Time" @default.
• W2510191442 cites W130123586 @default.
• W2510191442 cites W1530581016 @default.
• W2510191442 cites W1535669030 @default.
• W2510191442 cites W1556219185 @default.
• W2510191442 cites W180242331 @default.
• W2510191442 cites W1967187838 @default.
• W2510191442 cites W1998325344 @default.
• W2510191442 cites W2046816920 @default.
• W2510191442 cites W2048442462 @default.
• W2510191442 cites W2073459066 @default.
• W2510191442 cites W2086943813 @default.
• W2510191442 cites W2090948651 @default.
• W2510191442 cites W2101012814 @default.
• W2510191442 cites W2108399535 @default.
• W2510191442 cites W2115665694 @default.
• W2510191442 cites W2116762767 @default.
• W2510191442 cites W2118190603 @default.
• W2510191442 cites W2118858186 @default.
• W2510191442 cites W2123297508 @default.
• W2510191442 cites W2138309709 @default.
• W2510191442 cites W2141650448 @default.
• W2510191442 cites W2142827986 @default.
• W2510191442 cites W2142838865 @default.
• W2510191442 cites W2143776582 @default.
• W2510191442 cites W2150593711 @default.
• W2510191442 cites W2154200889 @default.
• W2510191442 cites W2156499390 @default.
• W2510191442 cites W2164573470 @default.
• W2510191442 cites W2204035083 @default.
• W2510191442 doi "https://doi.org/10.1609/aaai.v30i1.10259" @default.
• W2510191442 hasPublicationYear "2016" @default.
• W2510191442 type Work @default.
• W2510191442 sameAs 2510191442 @default.
• W2510191442 citedByCount "80" @default.
• W2510191442 countsByYear W25101914422015 @default.
• W2510191442 countsByYear W25101914422016 @default.
• W2510191442 countsByYear W25101914422017 @default.
• W2510191442 countsByYear W25101914422018 @default.
• W2510191442 countsByYear W25101914422019 @default.
• W2510191442 countsByYear W25101914422020 @default.
• W2510191442 countsByYear W25101914422021 @default.
• W2510191442 countsByYear W25101914422022 @default.
• W2510191442 countsByYear W25101914422023 @default.
• W2510191442 crossrefType "journal-article" @default.
• W2510191442 hasAuthorship W2510191442A5003040843 @default.
• W2510191442 hasAuthorship W2510191442A5044677020 @default.
• W2510191442 hasAuthorship W2510191442A5078613749 @default.
• W2510191442 hasAuthorship W2510191442A5089890773 @default.
• W2510191442 hasBestOaLocation W25101914421 @default.
• W2510191442 hasConcept C106131492 @default.
• W2510191442 hasConcept C107673813 @default.
• W2510191442 hasConcept C111350023 @default.
• W2510191442 hasConcept C11413529 @default.
• W2510191442 hasConcept C114466953 @default.
• W2510191442 hasConcept C117160843 @default.
• W2510191442 hasConcept C118615104 @default.
• W2510191442 hasConcept C119857082 @default.
• W2510191442 hasConcept C126255220 @default.
• W2510191442 hasConcept C140779682 @default.
• W2510191442 hasConcept C154945302 @default.
• W2510191442 hasConcept C177264268 @default.
• W2510191442 hasConcept C199360897 @default.
• W2510191442 hasConcept C207968372 @default.
• W2510191442 hasConcept C31972630 @default.
• W2510191442 hasConcept C33923547 @default.
• W2510191442 hasConcept C41008148 @default.
• W2510191442 hasConcept C73555534 @default.
• W2510191442 hasConcept C98763669 @default.
• W2510191442 hasConceptScore W2510191442C106131492 @default.
• W2510191442 hasConceptScore W2510191442C107673813 @default.
• W2510191442 hasConceptScore W2510191442C111350023 @default.
• W2510191442 hasConceptScore W2510191442C11413529 @default.
• W2510191442 hasConceptScore W2510191442C114466953 @default.
• W2510191442 hasConceptScore W2510191442C117160843 @default.
• W2510191442 hasConceptScore W2510191442C118615104 @default.
• W2510191442 hasConceptScore W2510191442C119857082 @default.
• W2510191442 hasConceptScore W2510191442C126255220 @default.
• W2510191442 hasConceptScore W2510191442C140779682 @default.
• W2510191442 hasConceptScore W2510191442C154945302 @default.
• W2510191442 hasConceptScore W2510191442C177264268 @default.
• W2510191442 hasConceptScore W2510191442C199360897 @default.
• W2510191442 hasConceptScore W2510191442C207968372 @default.
• W2510191442 hasConceptScore W2510191442C31972630 @default.
• W2510191442 hasConceptScore W2510191442C33923547 @default.
• W2510191442 hasConceptScore W2510191442C41008148 @default.
• W2510191442 hasConceptScore W2510191442C73555534 @default.
• W2510191442 hasConceptScore W2510191442C98763669 @default.
• W2510191442 hasIssue "1" @default.
• W2510191442 hasLocation W25101914421 @default.
• W2510191442 hasOpenAccess W2510191442 @default.
• W2510191442 hasPrimaryLocation W25101914421 @default.

• next