Poster
On Connected Sublevel Sets in Deep Learning
Quynh Nguyen
Pacific Ballroom #92
Keywords: [ Deep Learning Theory ]
[
Abstract
]
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.
Live content is unavailable. Log in and register to view live content