2000 character limit reached
Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning
Published 16 Jul 2020 in cs.LG and stat.ML | (2007.08243v3)
Abstract: We analyse the pruning procedure behind the lottery ticket hypothesis arXiv:1803.03635v5, iterative magnitude pruning (IMP), when applied to linear models trained by gradient flow. We begin by presenting sufficient conditions on the statistical structure of the features under which IMP prunes those features that have smallest projection onto the data. Following this, we explore IMP as a method for sparse estimation.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.