| 
|
Quote: in high dimensional spaces, the ratio between nearest and farthest neighbor is almost one; nearest neighbor is ill defined
topics >
all references >
references a-b >
Topic:
geometry
Topic:
information retrieval by relevance
Topic:
fractal geometry
Quotation Skeleton
It has been argued in [Beyer, Goldstein, Ramakrishnan, Shaft, ICDT Conf Proc, LNCS?, 1999], that under … farthest neighbors to a given target in high … such a case, the nearest neighbor problem becomes … we show that the relative contrasts of the … This means that the L_1 distance metric (Manhattan … [etc] … we examine the behavior of fractional distance metrics, … metric is even more effective at preserving the … . [p. 431] the L_.infinity. metric only looks at … [p. 432] The L_0.1 distance metric is most robust … slowest rate. Google-1 Google-2
Copyright clearance needed for quotation.
Additional Titles
Quote: use fractional distance metrics to preserve proximity in high dimensional spaces;
Topic: geometry (33 items)
Topic: information retrieval by relevance (32 items)
Topic: fractal geometry (8 items)