Deep Network Approximation in Terms of Intrinsic Parameters. (arXiv:2111.07964v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2111.07964

One of the arguments to explain the success of deep learning is the powerful
approximation capacity of deep neural networks. Such capacity is generally
accompanied by the explosive growth of the number of parameters, which, in
turn, leads to high computational costs. It is of great interest to ask whether
we can achieve successful deep learning with a small number of learnable
parameters adapting to the target function. From an approximation perspective,
this paper shows that the number of parameters …

approximation arxiv deep lg network terms