Y
Hacker News
new
|
ask
|
show
|
jobs
by
sdpmas
92 days ago
oh ensemble can be distilled to a single model easily.
1 comments
SknCode
92 days ago
How?
link
sigmoid10
92 days ago
Same way you distill any model. Training data efficiency matters only while you train the source model/ensemble. Once you have that you are purely compute bound during distillation.
link