ResearchTrend.AI
Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping
v1v2 (latest)

Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping

Journal of machine learning research (JMLR), 2021
Xuran Meng
Jianfeng Yao
ArXiv (abs)PDFHTML

Papers citing "Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping"

6 / 6 papers shown
Early-stopping for Transformer model training
Early-stopping for Transformer model training
Jing He
Hua Jiang
Cheng Li
Siqian Xin
Shuzhen Yang
172
0
0
17 Oct 2025
Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
Fairness Feedback Loops: Training on Synthetic Data Amplifies BiasConference on Fairness, Accountability and Transparency (FAccT), 2024
Sierra Wyllie
Ilia Shumailov
Nicolas Papernot
285
61
0
12 Mar 2024
Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks
Heavy-Tailed Regularization of Weight Matrices in Deep Neural NetworksInternational Conference on Artificial Neural Networks (ICANN), 2023
Xuanzhe Xiao
Zengyi Li
Chuanlong Xie
Fengwei Zhou
374
5
0
06 Apr 2023
Per-Example Gradient Regularization Improves Learning Signals from Noisy Data
Per-Example Gradient Regularization Improves Learning Signals from Noisy Data
Xuran Meng
Yuan Cao
Difan Zou
324
9
0
31 Mar 2023
Deep Learning Weight Pruning with RMT-SVD: Increasing Accuracy and Reducing Overfitting
Deep Learning Weight Pruning with RMT-SVD: Increasing Accuracy and Reducing Overfitting
Yitzchak Shmalo
Jonathan Jenkins
Oleksii Krupchytskyi
236
5
0
15 Mar 2023
Spectral Evolution and Invariance in Linear-width Neural Networks
Spectral Evolution and Invariance in Linear-width Neural NetworksNeural Information Processing Systems (NeurIPS), 2022
Zhichao Wang
A. Engel
Anand D. Sarwate
Ioana Dumitriu
Tony Chiang
307
28
0
11 Nov 2022