Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks
This work addresses a specific bottleneck in deep learning optimization for researchers and practitioners, offering an incremental improvement over existing adaptive methods.
The paper tackled the problem of inaccurate Hessian approximation in adaptive learning rate algorithms like RMSProp due to noise from stochastic optimization, proposing SDProp, a novel algorithm based on covariance matrix preconditioning that showed improved efficiency and effectiveness over RMSProp and its variants for various neural networks.
Adaptive learning rate algorithms such as RMSProp are widely used for training deep neural networks. RMSProp offers efficient training since it uses first order gradients to approximate Hessian-based preconditioning. However, since the first order gradients include noise caused by stochastic optimization, the approximation may be inaccurate. In this paper, we propose a novel adaptive learning rate algorithm called SDProp. Its key idea is effective handling of the noise by preconditioning based on covariance matrix. For various neural networks, our approach is more efficient and effective than RMSProp and its variant.