Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win

2020/10/07 by Utku Evci, Yani Ioannou, Evci, Utku +5 · 3 citations
Computer Science · #68T07 #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Stochastic Gradient Optimization Techniques

paper · pdf · doi:10.48550/arxiv.2010.03533

openalex publication_date 2020/10/07 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win - AAAI 2022 Poster

Cited by

• Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks
• Winning the Lottery by Preserving Network Training Dynamics with Concrete Ticket Search
• Investigating the Lottery Ticket Hypothesis for Variational Quantum Circuits

Related

• Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization
• Deconstructing the Structure of Sparse Neural Networks
• Dual Lottery Ticket Hypothesis
• Spending Your Winning Lottery Better After Drawing It
• Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability