S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima

Abstract

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss surface that can demonstrate high generalization capability. Weight noise injection has been extensively studied for finding flat minima using the SGD method. We devise a new weight-noise injection-based SGD method that adds symmetrical noises to the DNN weights. The training with symmetrical noise evaluates the loss surface at two adjacent points, by which convergence to sharp minima can be avoided. Fixed-magnitude symmetric noises are added to minimize training instability. The proposed method is compared with the conventional SGD method and previous weight-noise injection algorithms using convolutional neural networks for image classification. Particularly, performance improvements in large batch training are demonstrated. This method shows superior performance compared with conventional SGD and weight-noise injection methods regardless of the batch-size and learning rate scheduling algorithms.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Recurrent Neural Network Regularization
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Large Batch Training of Convolutional Networks
• Improving Generalization Performance by Switching from Adam to SGD
• An Investigation into Neural Net Optimization via Hessian Eigenvalue Density