2021/07/01 by Uchizawa, Kei, Abe, Haruki
#Computational Complexity (cs.CC) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
paper · doi:10.48550/arxiv.2107.00223
In this paper, we investigate computational power of threshold circuits and other theoretical models of neural networks in terms of the following four complexity measures: size (the number of gates), depth, weight and energy. Here the energy complexity of a circuit measures sparsity of their computation, and is defined as the maximum number of gates outputting non-zero values taken over all the input assignments. As our main result, we prove that any threshold circuit C of size s, depth d, energy e and weight w satisfies log (rk(MC)) ≤ ed (log s + log w + log n), where rk(MC) is the rank of the communication matrix MC of a 2n-variable Boolean function that C computes. Thus, such a threshold circuit C is able to compute only a Boolean function of which communication matrix has rank bounded by a product of logarithmic factors of s,w and linear factors of d,e. This implies an exponential lower bound on the size of even sublinear-depth threshold circuit if energy and weight are sufficiently small. For other models of neural networks such as a discretized ReLE circuits and decretized sigmoid circuits, we prove that a similar inequality also holds for a discretized circuit C: rk(MC) = O(ed(log s + log w + log n)3).