2020/07/16 by Bryn Elesedy, Elesedy, Bryn, Varun Kanade +3 · 6 citations
Computer Science · Economics, Econometrics and Finance · Mathematics · Physics and Astronomy · #Algorithm #Artificial intelligence #Computer science #Econometrics #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #I.5.1 #Lottery #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Magnitude (astronomy) #Mathematics #Matrix (chemical analysis) #Model Reduction and Neural Networks #Physics #Projection (relational algebra) #Pruning #Sports Analytics and Performance #Statistics #Ticket #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2007.08243
published in arXiv (Cornell University) (Cornell University) · Updated for Sparsity in Neural Networks Workshop
openalex publication_date 2020/07/16 · arxiv created 2021/07/05 · arxiv updated 2021/07/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
We analyse the pruning procedure behind the lottery ticket hypothesis\narXiv:1803.03635v5, iterative magnitude pruning (IMP), when applied to linear\nmodels trained by gradient flow. We begin by presenting sufficient conditions\non the statistical structure of the features under which IMP prunes those\nfeatures that have smallest projection onto the data. Following this, we\nexplore IMP as a method for sparse estimation.\n