Adaptive Weight Decay for Deep Neural Networks

Abstract

Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model. One of the most popular regularization algorithms is to impose L-2 penalty on the model parameters resulting in the decay of parameters, called weight-decay, and the decay rate is generally constant to all the model parameters in the course of optimization. In contrast to the previous approach based on the constant rate of weight-decay, we propose to consider the residual that measures dissimilarity between the current state of model and observations in the determination of the weight-decay for each parameter in an adaptive way, called adaptive weight-decay (AdaDecay) where the gradient norms are normalized within each layer and the degree of regularization for each parameter is determined in proportional to the magnitude of its gradient using the sigmoid function. We empirically demonstrate the effectiveness of AdaDecay in comparison to the state-of-the-art optimization algorithms using popular benchmark datasets: MNIST, Fashion-MNIST, and CIFAR-10 with conventional neural network models ranging from shallow to deep. The quantitative evaluation of our proposed algorithm indicates that AdaDecay improves generalization leading to better accuracy across all the datasets and models.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Understanding deep learning requires rethinking generalization
• Don't Decay the Learning Rate, Increase the Batch Size
• A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets
• Variational Dropout and the Local Reparameterization Trick
• Scalable Bayesian Optimization Using Deep Neural Networks
• Sharp Minima Can Generalize For Deep Nets
• The Shattered Gradients Problem: If resnets are the answer, then what is the question?
• Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization
• The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
• A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates