A finite sample analysis of the double descent phenomenon for ridge function estimation
share
Recent extensive numerical experiments in high scale machine learning have allowed to uncover a quite counterintuitive phase transition, as a function of the ratio between the sample size and the number of parameters in the model. As the number of parameters p approaches the sample size n, the generalisation error (a.k.a. testing error) increases, but it many cases, it starts decreasing again past the threshold p=n. This surprising phenomenon, brought to the theoretical community attention in <cit.>, has been thorougly investigated lately, more specifically for simpler models than deep neural networks, such as the linear model when the parameter is taken to be the minimum norm solution to the least-square problem, mostly in the asymptotic regime when p and n tend to +∞; see e.g. <cit.>. In the present paper, we propose a finite sample analysis of non-linear models of ridge type, where we investigate the double descent phenomenon for both the estimation problem and the prediction problem. Our results show that the double descent phenomenon can be precisely demonstrated in non-linear settings and complements recent works of <cit.> and <cit.>. Our analysis is based on efficient but elementary tools closely related to the continuous Newton method <cit.>.
READ FULL TEXT