An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity

02/03/2019
by   Yingzhen Yang, et al.
0

Regularization of Deep Neural Networks (DNNs) for the sake of improving their generalization capability is important and challenging. The development in this line benefits theoretical foundation of DNNs and promotes their usability in different areas of artificial intelligence. In this paper, we investigate the role of Rademacher complexity in improving generalization of DNNs and propose a novel regularizer rooted in Local Rademacher Complexity (LRC). While Rademacher complexity is well known as a distribution-free complexity measure of function class that help boost generalization of statistical learning methods, extensive study shows that LRC, its counterpart focusing on a restricted function class, leads to sharper convergence rates and potential better generalization given finite training sample. Our LRC based regularizer is developed by estimating the complexity of the function class centered at the minimizer of the empirical loss of DNNs. Experiments on various types of network architecture demonstrate the effectiveness of LRC regularization in improving generalization. Moreover, our method features the state-of-the-art result on the CIFAR-10 dataset with network architecture found by neural architecture search.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/18/2019

Foothill: A Quasiconvex Regularization Function

Deep neural networks (DNNs) have demonstrated success for many supervise...
research
11/19/2019

Information-Theoretic Local Minima Characterization and Regularization

Recent advances in deep learning theory have evoked the study of general...
research
11/11/2019

An empirical study of the relation between network architecture and complexity

In this preregistration submission, we propose an empirical study of how...
research
05/17/2020

FuCiTNet: Improving the generalization of deep learning networks by the fusion of learned class-inherent transformations

It is widely known that very small datasets produce overfitting in Deep ...
research
10/18/2017

Stochastic Weighted Function Norm Regularization

Deep neural networks (DNNs) have become increasingly important due to th...
research
07/07/2018

Anytime Neural Prediction via Slicing Networks Vertically

The pioneer deep neural networks (DNNs) have emerged to be deeper or wid...
research
12/02/2019

The intriguing role of module criticality in the generalization of deep networks

We study the phenomenon that some modules of deep neural networks (DNNs)...

Please sign up or login with your details

Forgot password? Click here to reset