Fast generalization error bound of deep learning without scale invariance of activation functions
This resolves a theoretical gap for researchers in deep learning theory by demonstrating that scale invariance is not essential for fast convergence, broadening the applicability of existing frameworks.
The paper tackles the problem of deriving fast generalization error bounds for deep neural networks with non-scale-invariant activation functions, showing that such functions can achieve the same tight bound as scale-invariant ones, specifically matching the fast rate from prior work.
In theoretical analysis of deep learning, discovering which features of deep learning lead to good performance is an important task. In this paper, using the framework for analyzing the generalization error developed in Suzuki (2018), we derive a fast learning rate for deep neural networks with more general activation functions. In Suzuki (2018), assuming the scale invariance of activation functions, the tight generalization error bound of deep learning was derived. They mention that the scale invariance of the activation function is essential to derive tight error bounds. Whereas the rectified linear unit (ReLU; Nair and Hinton, 2010) satisfies the scale invariance, the other famous activation functions including the sigmoid and the hyperbolic tangent functions, and the exponential linear unit (ELU; Clevert et al., 2016) does not satisfy this condition. The existing analysis indicates a possibility that a deep learning with the non scale invariant activations may have a slower convergence rate of $O(1/\sqrt{n})$ when one with the scale invariant activations can reach a rate faster than $O(1/\sqrt{n})$. In this paper, without the scale invariance of activation functions, we derive the tight generalization error bound which is essentially the same as that of Suzuki (2018). From this result, at least in the framework of Suzuki (2018), it is shown that the scale invariance of the activation functions is not essential to get the fast rate of convergence. Simultaneously, it is also shown that the theoretical framework proposed by Suzuki (2018) can be widely applied for analysis of deep learning with general activation functions.