FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1520260139> ?p ?o ?g. }

• W1520260139 endingPage "49" @default.
• W1520260139 startingPage "37" @default.
• W1520260139 abstract "Aiming to unify known results about clustering mixtures of distributions under separation conditions, Kumar and Kannan [1] introduced a deterministic condition for clustering datasets. They showed that this single deterministic condition encompasses many previously studied clustering assumptions. More specifically, their proximity condition requires that in the target k-clustering, the projection of a point x onto the line joining its cluster center μ and some other center μ′, is a large additive factor closer to μ than to μ′. This additive factor can be roughly described as k times the spectral norm of the matrix representing the differences between the given (known) dataset and the means of the (unknown) target clustering. Clearly, the proximity condition implies center separation – the distance between any two centers must be as large as the above mentioned bound. In this paper we improve upon the work of Kumar and Kannan [1] along several axes. First, we weaken the center separation bound by a factor of $sqrt{k}$ , and secondly we weaken the proximity condition by a factor of k (in other words, the revised separation condition is independent of k). Using these weaker bounds we still achieve the same guarantees when all points satisfy the proximity condition. Under the same weaker bounds, we achieve even better guarantees when only (1 − ε)-fraction of the points satisfy the condition. Specifically, we correctly cluster all but a (ε + O(1/c 4))-fraction of the points, compared to O(k 2 ε)-fraction of [1], which is meaningful even in the particular setting when ε is a constant and k = ω(1). Most importantly, we greatly simplify the analysis of Kumar and Kannan. In fact, in the bulk of our analysis we ignore the proximity condition and use only center separation, along with the simple triangle and Markov inequalities. Yet these basic tools suffice to produce a clustering which (i) is correct on all but a constant fraction of the points, (ii) has k-means cost comparable to the k-means cost of the target clustering, and (iii) has centers very close to the target centers. Our improved separation condition allows us to match the results of the Planted Partition Model of McSherry [2], improve upon the results of Ostrovsky et al [3], and improve separation results for mixture of Gaussian models in a particular setting." @default.
• W1520260139 created "2016-06-24" @default.
• W1520260139 creator A5056617357 @default.
• W1520260139 creator A5087418764 @default.
• W1520260139 date "2012-01-01" @default.
• W1520260139 modified "2023-10-13" @default.
• W1520260139 title "Improved Spectral-Norm Bounds for Clustering" @default.
• W1520260139 cites W1574816920 @default.
• W1520260139 cites W1605711022 @default.
• W1520260139 cites W1969015668 @default.
• W1520260139 cites W1998325344 @default.
• W1520260139 cites W2012828271 @default.
• W1520260139 cites W2014562510 @default.
• W1520260139 cites W2026302946 @default.
• W1520260139 cites W2059971059 @default.
• W1520260139 cites W2081605725 @default.
• W1520260139 cites W2133361319 @default.
• W1520260139 cites W2911808754 @default.
• W1520260139 cites W2952995770 @default.
• W1520260139 cites W4235023610 @default.
• W1520260139 cites W4254734767 @default.
• W1520260139 doi "https://doi.org/10.1007/978-3-642-32512-0_4" @default.
• W1520260139 hasPublicationYear "2012" @default.
• W1520260139 type Work @default.
• W1520260139 sameAs 1520260139 @default.
• W1520260139 citedByCount "37" @default.
• W1520260139 countsByYear W15202601392013 @default.
• W1520260139 countsByYear W15202601392014 @default.
• W1520260139 countsByYear W15202601392015 @default.
• W1520260139 countsByYear W15202601392016 @default.
• W1520260139 countsByYear W15202601392017 @default.
• W1520260139 countsByYear W15202601392018 @default.
• W1520260139 countsByYear W15202601392019 @default.
• W1520260139 countsByYear W15202601392020 @default.
• W1520260139 countsByYear W15202601392021 @default.
• W1520260139 countsByYear W15202601392022 @default.
• W1520260139 countsByYear W15202601392023 @default.
• W1520260139 crossrefType "book-chapter" @default.
• W1520260139 hasAuthorship W1520260139A5056617357 @default.
• W1520260139 hasAuthorship W1520260139A5087418764 @default.
• W1520260139 hasBestOaLocation W15202601392 @default.
• W1520260139 hasConcept C105795698 @default.
• W1520260139 hasConcept C106487976 @default.
• W1520260139 hasConcept C11413529 @default.
• W1520260139 hasConcept C114614502 @default.
• W1520260139 hasConcept C118615104 @default.
• W1520260139 hasConcept C121332964 @default.
• W1520260139 hasConcept C134306372 @default.
• W1520260139 hasConcept C149629883 @default.
• W1520260139 hasConcept C158693339 @default.
• W1520260139 hasConcept C159985019 @default.
• W1520260139 hasConcept C164866538 @default.
• W1520260139 hasConcept C17744445 @default.
• W1520260139 hasConcept C178790620 @default.
• W1520260139 hasConcept C185592680 @default.
• W1520260139 hasConcept C191795146 @default.
• W1520260139 hasConcept C192562407 @default.
• W1520260139 hasConcept C199360897 @default.
• W1520260139 hasConcept C199539241 @default.
• W1520260139 hasConcept C2779463800 @default.
• W1520260139 hasConcept C33923547 @default.
• W1520260139 hasConcept C41008148 @default.
• W1520260139 hasConcept C57493831 @default.
• W1520260139 hasConcept C62520636 @default.
• W1520260139 hasConcept C73555534 @default.
• W1520260139 hasConcept C77553402 @default.
• W1520260139 hasConcept C8010536 @default.
• W1520260139 hasConcept C84545080 @default.
• W1520260139 hasConcept C92207270 @default.
• W1520260139 hasConceptScore W1520260139C105795698 @default.
• W1520260139 hasConceptScore W1520260139C106487976 @default.
• W1520260139 hasConceptScore W1520260139C11413529 @default.
• W1520260139 hasConceptScore W1520260139C114614502 @default.
• W1520260139 hasConceptScore W1520260139C118615104 @default.
• W1520260139 hasConceptScore W1520260139C121332964 @default.
• W1520260139 hasConceptScore W1520260139C134306372 @default.
• W1520260139 hasConceptScore W1520260139C149629883 @default.
• W1520260139 hasConceptScore W1520260139C158693339 @default.
• W1520260139 hasConceptScore W1520260139C159985019 @default.
• W1520260139 hasConceptScore W1520260139C164866538 @default.
• W1520260139 hasConceptScore W1520260139C17744445 @default.
• W1520260139 hasConceptScore W1520260139C178790620 @default.
• W1520260139 hasConceptScore W1520260139C185592680 @default.
• W1520260139 hasConceptScore W1520260139C191795146 @default.
• W1520260139 hasConceptScore W1520260139C192562407 @default.
• W1520260139 hasConceptScore W1520260139C199360897 @default.
• W1520260139 hasConceptScore W1520260139C199539241 @default.
• W1520260139 hasConceptScore W1520260139C2779463800 @default.
• W1520260139 hasConceptScore W1520260139C33923547 @default.
• W1520260139 hasConceptScore W1520260139C41008148 @default.
• W1520260139 hasConceptScore W1520260139C57493831 @default.
• W1520260139 hasConceptScore W1520260139C62520636 @default.
• W1520260139 hasConceptScore W1520260139C73555534 @default.
• W1520260139 hasConceptScore W1520260139C77553402 @default.
• W1520260139 hasConceptScore W1520260139C8010536 @default.
• W1520260139 hasConceptScore W1520260139C84545080 @default.
• W1520260139 hasConceptScore W1520260139C92207270 @default.
• W1520260139 hasLocation W15202601391 @default.

• next