Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of
Neurons

Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons

12 March 2024

Simon Dufort-Labbé

Evgenii Nikishin

Pierre-Luc Bacon

Papers citing "Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons"

6 / 6 papers shown

Title
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models Iman Mirzadeh Keivan Alizadeh-Vahid Sachin Mehta C. C. D. Mundo Oncel Tuzel Golnoosh Samei Mohammad Rastegari Mehrdad Farajtabar 118 58 0 06 Oct 2023
Dynamic Sparse Training with Structured Sparsity Mike Lasby A. Golubeva Utku Evci Mihai Nica Yani Andrew Ioannou 21 19 0 03 May 2023
JaxPruner: A concise library for sparsity research Jooyoung Lee Wonpyo Park Nicole Mitchell Jonathan Pilault J. Obando-Ceron ... Hong-Seok Kim Yann N. Dauphin Karolina Dziugaite P. S. Castro Utku Evci 26 13 0 27 Apr 2023
The Primacy Bias in Deep Reinforcement Learning Evgenii Nikishin Max Schwarzer P. DÓro Pierre-Luc Bacon Aaron C. Courville OnRL 85 178 0 16 May 2022
Structured Pruning for Efficient ConvNets via Incremental Regularization Huan Wang Qiming Zhang Yuehai Wang Haoji Hu 3DPC 33 44 0 20 Nov 2018
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 273 2,878 0 15 Sep 2016