RT @davisidarta: @yaroslavvb If I'm not mistaken (please correct me if I am), Aggarwal, Hinneburg, and Keim were the first to explore this…
1,181 followers
1,438 followers
@yaroslavvb If I'm not mistaken (please correct me if I am), Aggarwal, Hinneburg, and Keim were the first to explore this phenomenon: https://t.co/PFIpAZeG5S https://t.co/fJChFlkoxm
682 followers
In high dimension, Manhattan distance (L1 norm) is consistently more preferable than the Euclidean distance metric (L2 norm). Fractional distance metrics are more effective at preserving the meaningfulness of proximity measures. https://t.co/uAtzkaOzjJ
682 followers
In high dimension, "proximity, distance or nearest neighbor may not even be qualitatively meaningful"; "the ratio of the distances of the nearest and farthest neighbors to a given target is almost 1: The nearest neighbour problem becomes ill defined." ht