The Law of Parsimony in Gradient Descent for Learning Deep Linear
Networks

The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks

1 June 2023

Qing Qu

Papers citing "The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks"

5 / 5 papers shown

Title
Embedded Visual Prompt Tuning Wenqiang Zu Shenghao Xie Qing Zhao Guoqi Li Lei Ma VLM MedIm 44 9 0 01 Jul 2024
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization Hancheng Min Enrique Mallada René Vidal MLT 30 19 0 24 Jul 2023
Perturbation Analysis of Neural Collapse Tom Tirer Haoxiang Huang Jonathan Niles-Weed AAML 30 23 0 29 Oct 2022
Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training Cong Fang Hangfeng He Qi Long Weijie J. Su FAtt 117 164 0 29 Jan 2021
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 220 347 0 14 Jun 2018