Re:Every Model Learned by Gradient Descent Is Approximately ...
by eugenhotaj on Sunday December 06, 2020 @12:28PM
(#25324969)
Fair enough, but the number of support vectors for non trivial problems is still pretty large (as I understand but could be wrong), e.g. 20-30% of the dataset. Having to iterate over 30% of say imagenet on each batch of predictions seems unfeasible.
[ Parent
| on HN ]
There are no comments on this comment yet.