One-Step Early Stopping Strategy using Neural Tangent Kernel Theory and Rademacher Complexity

Autor:	Xavier, Daniel Martin, Chamoin, Ludovic, Jerray, Jawher, Fribourg, Laurent
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Electrical Engineering and Systems Science - Systems and Control
Druh dokumentu:	Working Paper
Popis:	The early stopping strategy consists in stopping the training process of a neural network (NN) on a set $S$ of input data before training error is minimal. The advantage is that the NN then retains good generalization properties, i.e. it gives good predictions on data outside $S$, and a good estimate of the statistical error (``population loss'') is obtained. We give here an analytical estimation of the optimal stopping time involving basically the initial training error vector and the eigenvalues of the ``neural tangent kernel''. This yields an upper bound on the population loss which is well-suited to the underparameterized context (where the number of parameters is moderate compared with the number of data). Our method is illustrated on the example of an NN simulating the MPC control of a Van der Pol oscillator. Comment: 7 pages, 2 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.18806 Zobrazit plný text záznamu View this record from Arxiv