OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns
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. This uniform treatment ignores that different layers may follow different structural dynamics and therefore may require different regularization strengths. In this work, we propose OUIDecay, an adaptive layer-wise and time-dependent weight decay scheduler for CNNs driven by the Overfitting-Underfitting Indicator (OUI), an activation-based metric previously shown to provide early information about regularization quality. OUIDecay uses a lightweight batch-based formulation of OUI to monitor the structural behavior of each layer online and periodically rescales its weight decay relative to the other layers in the network. Unlike gradient-based adaptive decay methods, our approach relies on functional information extracted from activation patterns and does not require validation data. Experiments on EfficientNet-B0 with Stanford Cars, ResNet50 with Food101, DenseNet121 with CIFAR100, and MobileNetV2 with CIFAR10 show that OUIDecay achieves the best mean best-validation-loss in 7 out of 8 evaluated settings. These results indicate that activation-driven weight decay adaptation is a practical and effective alternative to fixed decay and gradient-based adaptive decay, while keeping the method lightweight and suitable for online use.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
Weight decay is a standard regularization technique for training large language models (LLMs). While it is common to assign a uniform decay rate to every layer, this approach overlooks the structural diversity of LLMs an…
DiversityStochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, m…
General Classificationimage-classificationLanguage Modelingspeech-recognition+2Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, m…
General Classificationimage-classificationImage ClassificationLanguage Modeling+5Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation
In recent years, end-to-end learnt video codecs have demonstrated their potential to compete with conventional coding algorithms in term of compression efficiency. However, most learning-based video compression models ar…
DecoderVideo CompressionOrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling
Muon improves neural-network training by orthogonalizing matrix-valued updates, but it leaves each layer's update magnitude controlled mostly by a global learning rate. We introduce OrScale, a trust-ratio extension of Mu…