Crosspolytope LSH and its multiprobe variant for approximate angular similarity #378
alexklibisz
started this conversation in
Ideas
Replies: 1 comment
-
|
Maybe another possible optimization for cosine/angular similarity |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
See this paper: https://arxiv.org/abs/1509.02897
AFAIK, this is SOA for angular LSH methods.
Beta Was this translation helpful? Give feedback.
All reactions