A finite sample analysis of the benign overfitting phenomenon for ridge function estimation

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 increases, but surprisingly, it starts decreasing again past the threshold p=n. This phenomenon, brought to the theoretical community attention in citebelkin2019reconciling, has been thoroughly 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-squares problem, firstly in the asymptotic regime when p and n tend to infinity, see e.g. citehastie2019surprises, and recently in the finite dimensional regime and more specifically for linear models citebartlett2020benign, citetsigler2020benign, citelecue2022geometrical. In the present paper, we propose a finite sample analysis of non-linear models of textitridge type, where we investigate the textitoverparametrised regime of the double descent phenomenon for both the textitestimation problem and the textitprediction problem. Our results provide a precise analysis of the distance of the best estimator from the true parameter as well as a generalisation bound which complements recent works of citebartlett2020benign and citechinot2020benign. Our analysis is based on tools closely related to the continuous Newton method citeneuberger2007continuous and a refined quantitative analysis of the performance in prediction of the minimum ℓ2-norm solution.