Max-Affine Spline Insights Into Deep Network Pruning. (arXiv:2101.02338v4 [cs.LG] UPDATED)

In this paper, we study the importance of pruning in Deep Networks (DNs) and
the yin & yang relationship between (1) pruning highly overparametrized DNs
that have been trained from random initialization and (2) training small DNs
that have been "cleverly" initialized. As in most cases practitioners can only
resort to random initialization, there is a strong need to develop a grounded
understanding of DN pruning. Current literature remains largely empirical,
lacking a theoretical understanding of how pruning affects DNs' …

arxiv insights lg network pruning spline