paper-with-me

Papers

Regularizing Neural Networks via Adversarial Model Perturbation

2020-10-10 · CVPR 2021 1 · Yaowei Zheng, Richong Zhang, Yongyi Mao

Effective regularization techniques are highly desired in deep learning for alleviating overfitting and improving generalization. This work proposes a new regularization scheme, based on the understanding that the flat local minima of the empirical risk cause the model to generalize better. This scheme is referred to as adversarial model perturbation (AMP), where instead of directly minimizing the empirical risk, an alternative "AMP loss" is minimized via SGD. Specifically, the AMP loss is obtained from the empirical risk by applying the "worst" norm-bounded perturbation on each point in the parameter space. Comparing with most existing regularization schemes, AMP has strong theoretical justifications, in that minimizing the AMP loss can be shown theoretically to favour flat local minima of the empirical risk. Extensive experiments on various modern deep architectures establish AMP as a new state of the art among regularization schemes. Our code is available at https://github.com/hiyouga/AMP-Regularizer.

📄 PDF Abstract BibTeX arXiv:2010.04925

Code (1)

hiyouga/AMP-Regularizer 공식 구현 pytorch

Tasks

Image Classificationmodel

Methods 이 논문이 사용한 방법론

AMP Based on the understanding that the flat local minima of the empirical risk cause the model to generalize better. Adversarial Model Perturbation (AMP) improves generalization via…
Cutout Cutout is an image augmentation and regularization technique that randomly masks out square regions of input during training. and can be used to improve the robustness and…
AutoAugment 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Ethereum Customer Service Number +1-833-534-1729 설명 없음
PyramidNet 설명 없음

Similar Papers 제목 키워드 기반

Improving Resistance to Adversarial Deformations by Regularizing Gradients

2020-08-29 · Pengfei Xia, Bin Li

Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed to defend against intensity perturbatio…

δ-SAM: Sharpness-Aware Minimization with Dynamic Reweighting

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adve…

Sharpness-Aware Minimization with Dynamic Reweighting

2021-12-16 · Wenxuan Zhou, Fangyu Liu, huan zhang, Muhao Chen

Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adve…

Natural Language Understanding

Improving Back-Propagation by Adding an Adversarial Gradient

2015-10-14 · Arild Nøkland

The back-propagation algorithm is widely used for learning in artificial neural networks. A challenge in machine learning is to create models that generalize to new data samples not seen in the training data. Recently, a…

BIG-bench Machine LearningGeneral Classification

Adversarial Training Methods for Semi-Supervised Text Classification

2016-05-25 · Takeru Miyato, Andrew M. Dai, Ian Goodfellow

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both metho…

ClassificationGeneral ClassificationSemi-Supervised Text ClassificationSentiment Analysis+2