Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty. (arXiv:2209.09658v2 [cs.LG] UPDATED)

Among attempts at giving a theoretical account of the success of deep neural
networks, a recent line of work has identified a so-called lazy training regime
in which the network can be well approximated by its linearization around
initialization. Here we investigate the comparative effect of the lazy (linear)
and feature learning (non-linear) regimes on subgroups of examples based on
their difficulty. Specifically, we show that easier examples are given more
weight in feature learning mode, resulting in faster training …

arxiv example impacts lazy linearization networks