I enjoyed reading this paper. The experiments are well-designed and it's well-written.
Much work on generalization of ML models deals with asymptotic bounds. Here, there's a precise way of measuring these, even for relatively large models with millions of parameters.
1 comment
[ 3.0 ms ] story [ 17.2 ms ] threadMuch work on generalization of ML models deals with asymptotic bounds. Here, there's a precise way of measuring these, even for relatively large models with millions of parameters.