paper-with-me

홈 › Papers

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

2024-11-27 · Daniel Martin Xavier, Ludovic Chamoin, Jawher Jerray, Laurent Fribourg

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.

📄 PDF Abstract BibTeX arXiv:2411.18806

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

Early stopping and non-parametric regression: An optimal data-dependent stopping rule

2013-06-15 · Garvesh Raskutti, Martin J. Wainwright, Bin Yu

The strategy of early stopping is a regularization technique based on choosing a stopping time for an iterative algorithm. Focusing on non-parametric regression in a reproducing kernel Hilbert space, we analyze the early…

regression

Generalization Ability of Wide Residual Networks

2023-05-29 · Jianfa Lai, Zixiong Yu, Songtao Tian, Qian Lin

In this paper, we study the generalization ability of the wide residual network on $\mathbb{S}^{d-1}$ with the ReLU activation function. We first show that as the width $m\rightarrow\infty$, the residual network kernel (…

regression

Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks

2022-12-28 · Ilja Kuzborskij, Csaba Szepesvári

We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in th…

Generalization of Overparametrized Deep Neural Network Under Noisy Observations

2021-09-29 · ICLR 2022 4 · Namjoon Suh, Hyunouk Ko, Xiaoming Huo

We study the generalization properties of the overparameterized deep neural network (DNN) with Rectified Linear Unit (ReLU) activations. Under the non-parametric regression framework, it is assumed that the ground-truth …

Adaptive Stopping Rule for Kernel-based Gradient Descent Algorithms

2020-01-09 · Xiangyu Chang, Shao-Bo Lin

In this paper, we propose an adaptive stopping rule for kernel-based gradient descent (KGD) algorithms. We introduce the empirical effective dimension to quantify the increments of iterations in KGD and derive an impleme…

Learning Theory