AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Directional Pruning of Deep Neural Networks

Shih-Kang Chao, Zhanyu Wang, Yue Xing, Guang Cheng

NeurIPS 2020 · Optimization › Implicit bias and generalization · approach: Stability-based generalization analysis · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use gRDA directional pruning instead of dense SGDResNet50 · ImageNettesting accuracy: around 68% -> 73%Improved
Use gRDA directional pruning instead of dense SGDVGG16 · CIFAR-10, epoch 600testing accuracy: 90.8178(0.1779) -> 91.01(0.1464)Improved
Use gRDA directional pruning instead of dense SGDWRN28x10 · CIFAR-10, epoch 200testing accuracy: 94.173(0.1127) -> 94.459(0.12)Improved
Use gRDA directional pruning instead of dense SGDWRN28x10 · CIFAR-100, epoch 200testing accuracy: 76.529(0.169) -> 76.996(0.1713)Improved
Add soft-thresholding to SGD updatesResNet50 · ImageNettime per iteration: 0.3964 (0.0183) -> 0.4582 (0.0166)Hurt
Add soft-thresholding to SGD updatesResNet50 · ImageNetpeak GPU memory: 14221 (376) -> 14159 (167)No clear effect
Increase μ from 0.51 to 0.6 (ablation)gRDA · CIFAR-10, VGG16, epoch 600sparsity: 61.4322(0.1143) -> 90.49(0.1593)Improved
Increase μ from 0.51 to 0.7 (ablation)gRDA · CIFAR-10, VGG16, epoch 600testing accuracy: 91.01(0.1464) -> 90.6433(0.224)Hurt
Increase μ from 0.51 to 0.7 (ablation)gRDA · CIFAR-10, VGG16, epoch 600sparsity: 61.4322(0.1143) -> 97.2167(0.0767)Improved
Increase μ from 0.55 to 0.65 (ablation)gRDA · CIFAR-100, WRN28x10, epoch 200sparsity: 90.2043(0.0508) -> 96.3042(0.0219)Improved
Increase μ from 0.55 to 0.65 (ablation)gRDA · CIFAR-100, WRN28x10, epoch 200testing accuracy: 76.996(0.1713) -> 76.853(0.1996)No clear effect
Use the standard ImageNet step-down learning-rate schedule (ablation)gRDA · ImageNettesting accuracy: nullHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy