2000 character limit reached
On Connected Sublevel Sets in Deep Learning (1901.07417v2)
Published 22 Jan 2019 in cs.LG and stat.ML
Abstract: This paper shows that every sublevel set of the loss function of a class of deep over-parameterized neural nets with piecewise linear activation functions is connected and unbounded. This implies that the loss has no bad local valleys and all of its global minima are connected within a unique and potentially very large global valley.