Considering Layerwise Importance in the Lottery Ticket Hypothesis

02/22/2023
by   Benjamin Vandersmissen, et al.
0

The Lottery Ticket Hypothesis (LTH) showed that by iteratively training a model, removing connections with the lowest global weight magnitude and rewinding the remaining connections, sparse networks can be extracted. This global comparison removes context information between connections within a layer. Here we study means for recovering some of this layer distributional context and generalise the LTH to consider weight importance values rather than global weight magnitudes. We find that given a repeatable training procedure, applying different importance metrics leads to distinct performant lottery tickets with little overlapping connections. This strongly suggests that lottery tickets are not unique

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset