Inspired by https://benchmarking.mlsafety.org/ideas#Honest%20models I am thinking that a near-optimally compressing network would have no space for cheating on the interactions in the model...somehow it implied we might want to train a model that plays with both training and choice of reducing its size—picking a part of itself it is most willing to sacrifice. This needs more thinking, I’m sure.
Inspired by https://benchmarking.mlsafety.org/ideas#Honest%20models I am thinking that a near-optimally compressing network would have no space for cheating on the interactions in the model...somehow it implied we might want to train a model that plays with both training and choice of reducing its size—picking a part of itself it is most willing to sacrifice.
This needs more thinking, I’m sure.