Created
September 2, 2019 14:19
-
-
Save mdouze/6cc12fa967e5d9911580ef633e559476 to your computer and use it in GitHub Desktop.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,
how exactly should we handle the transformation of query vectors ?
I can transform the database vectors and train the index offline, but when I receive queries, should I multiply the queries by the inverse L of the database vectors or should I transform the queries separately with their own inverse Cholesky decomposition of their covariance matrix ?
Thanks.