Hi, we define the interpolation threshold in Section 2 of the full paper (https://arxiv.org/abs/1912.02292)
as the point when the "Effective Model Complexity" = # of train samples.
Where the "Effective Model Complexity (EMC)" of a model + training procedure (w.r.t an input distribution) is the maximum number of samples from the distribution that the model+training can fit to ~0 train error.
Our experiments are consistent with the hypothesis that the double-descent peak occurs when EMC = n; that is, when the model+training is just barely able to fit the train set.
Where the "Effective Model Complexity (EMC)" of a model + training procedure (w.r.t an input distribution) is the maximum number of samples from the distribution that the model+training can fit to ~0 train error.
Our experiments are consistent with the hypothesis that the double-descent peak occurs when EMC = n; that is, when the model+training is just barely able to fit the train set.