Toward Understanding Why Adam Converges Faster Than SGD for Transformers

While stochastic gradient descent (SGD) is still the most popular optimization algorithm in deep learning, adaptive algorithms such as Adam have established empirical advantages over SGD in some deep learning applications such as training transformers. However, it remains a question why Adam converges significantly faster than SGD in these scenarios. In this paper, we explore one explanation of why Adam converges faster than SGD using a new concept directional sharpness. We argue that the performance of optimization algorithms is closely related to the directional sharpness of the update steps, and show SGD has much worse directional sharpness compared to adaptive algorithms. We further observe that only a small fraction of the coordinates causes the bad sharpness and slow convergence of SGD, and propose to use coordinate-wise clipping as a solution to SGD and other optimization algorithms. We demonstrate the effect of coordinate-wise clipping in sharpness reduction and speeding up the convergence of optimization algorithms under various settings, and conclude that the sharpness reduction effect of adaptive coordinate-wise scaling is the reason for Adam’s success in practice.