Stochastic Gradient Descent with Nonlinear Conjugate Gradient-Style Adaptive Momentum
This work addresses the computational burden of tuning momentum hyperparameters for deep neural network training, offering a more efficient optimization process for practitioners.
This paper proposes an adaptive momentum method for stochastic gradient descent (SGD) that eliminates the need for momentum hyperparameter tuning. It reduces classification errors for ResNet110 on CIFAR10 from 5.25% to 4.64% and on CIFAR100 from 23.75% to 20.03%.
Momentum plays a crucial role in stochastic gradient-based optimization algorithms for accelerating or improving training deep neural networks (DNNs). In deep learning practice, the momentum is usually weighted by a well-calibrated constant. However, tuning hyperparameters for momentum can be a significant computational burden. In this paper, we propose a novel \emph{adaptive momentum} for improving DNNs training; this adaptive momentum, with no momentum related hyperparameter required, is motivated by the nonlinear conjugate gradient (NCG) method. Stochastic gradient descent (SGD) with this new adaptive momentum eliminates the need for the momentum hyperparameter calibration, allows a significantly larger learning rate, accelerates DNN training, and improves final accuracy and robustness of the trained DNNs. For instance, SGD with this adaptive momentum reduces classification errors for training ResNet110 for CIFAR10 and CIFAR100 from $5.25\%$ to $4.64\%$ and $23.75\%$ to $20.03\%$, respectively. Furthermore, SGD with the new adaptive momentum also benefits adversarial training and improves adversarial robustness of the trained DNNs.