G-SGD - Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space.

It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient descent optimize the neural networks in the vector space of weights, which is, however, not positively scale-invariant. This mismatch may lead to problems during the optimization process. Then, a natural question is: can we construct a new vector space that is positively scale-invariant and sufficient to represent ReLU neural networks so as to better facilitate the optimization process? In this paper, we provide our positive answer to this question. First, we conduct a formal study on the positive scaling operators which forms a transformation group, denoted as G. We prove that the value of a path (i.e. the product of the weights along the path) in the neural network is invariant to positive scaling and the value vector of all the paths is sufficient to represent the neural networks under mild conditions. Second, we show that one can identify some basis paths out of all the paths and prove that the linear span of their value vectors (denoted as G-space) is an invariant space with lower dimension under the positive scaling group. Finally, we design stochastic gradient descent algorithm in G-space (abbreviated as G-SGD) to optimize the value vector of the basis paths of neural networks with little extra cost by leveraging back-propagation. Our experiments show that G-SGD significantly outperforms the conventional SGD algorithm in optimizing ReLU networks on benchmark datasets.