A Trace-restricted Kronecker-Factored Approximation to Natural Gradient
This work addresses the challenge of accelerating convergence for deep neural network training by providing a more effective second-order optimization method, which is significant for researchers and practitioners in deep learning.
This paper introduces Trace-restricted Kronecker-factored Approximate Curvature (TKFAC), a new approximation to the Fisher Information Matrix (FIM) for second-order optimization in deep neural networks. TKFAC decomposes FIM blocks as a trace-scaled Kronecker product of smaller matrices, demonstrating improved performance over state-of-the-art algorithms on various deep network architectures.
Second-order optimization methods have the ability to accelerate convergence by modifying the gradient through the curvature matrix. There have been many attempts to use second-order optimization methods for training deep neural networks. Inspired by diagonal approximations and factored approximations such as Kronecker-Factored Approximate Curvature (KFAC), we propose a new approximation to the Fisher information matrix (FIM) called Trace-restricted Kronecker-factored Approximate Curvature (TKFAC) in this work, which can hold the certain trace relationship between the exact and the approximate FIM. In TKFAC, we decompose each block of the approximate FIM as a Kronecker product of two smaller matrices and scaled by a coefficient related to trace. We theoretically analyze TKFAC's approximation error and give an upper bound of it. We also propose a new damping technique for TKFAC on convolutional neural networks to maintain the superiority of second-order optimization methods during training. Experiments show that our method has better performance compared with several state-of-the-art algorithms on some deep network architectures.