paper-with-me

홈 › Papers

SHADE: SHAnnon DEcay Information-Based Regularization for Deep Learning

2018-01-01 · ICLR 2018 1 · Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant representations in the regularizer and the learning of correlations between inputs and labels in the data fitting term. We explain why this quantity makes our model able to achieve invariance with respect to input variations. We empirically validate the efficiency of our approach to improve classification performances compared to standard regularization schemes on several standard architectures.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGeneral Classification

Similar Papers 제목 키워드 기반

SHADE: Information Based Regularization for Deep Learning

2018-04-29 · Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define …

Deep LearningGeneral Classification

SHADE: Information-Based Regularization for Deep Learning

2018-05-14 · Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define …

Deep LearningGeneral Classification

Improving Generalization by Controlling Label-Noise Information in Neural Network Weights

2020-02-19 · ICML 2020 1 · Hrayr Harutyunyan, Kyle Reing, Greg Ver Steeg, Aram Galstyan

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation s…

Data AugmentationGeneralization BoundsLearning with noisy labelsMemorization

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns

2026-05-11 · Alberto Fernández-Hernández, Jose I. Mestre, Cristian Pérez-Corral, Manuel F. Dolz 외 arxiv

Weight decay remains one of the most widely used regularization mechanisms for training convolutional neural networks, yet it is still commonly applied as a fixed coefficient shared by all layers throughout training. Thi…

Stable Weight Decay Regularization

2020-09-28 · Zeke Xie, Issei Sato, Masashi Sugiyama

Weight decay is a popular regularization technique for training of deep neural networks. Modern deep learning libraries mainly use $L_{2}$ regularization as the default implementation of weight decay. \citet{loshchilov20…