AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths

Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan Yao

ICML 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Pruning at initialization · 0 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 DessiLBI with momentum and weight decay instead of SGD Mom-WdAlexNet · ImageNet-2012Top-1 accuracy: 56.55 -> 57.09Improved
Use DessiLBI with momentum and weight decay instead of SGD Mom-WdAlexNet · ImageNet-2012Top-5 accuracy: 79.09 -> 79.86Improved
Use DessiLBI with momentum and weight decay instead of SGD NesterovResNet-18 · ImageNet-2012Top-1 accuracy: 70.19 -> 70.55Improved
Use DessiLBI with momentum and weight decay instead of SGD NesterovResNet-18 · ImageNet-2012Top-5 accuracy: 89.30 -> 89.56Improved
Add weight decay to DessiLBI with momentum (ablation)AlexNet · ImageNet-2012Top-1 accuracy: 56.23 -> 57.09Improved
Add weight decay to DessiLBI with momentum (ablation)AlexNet · ImageNet-2012Top-5 accuracy: 78.48 -> 79.86Improved
Add momentum and weight decay to naive DessiLBI (ablation)AlexNet · ImageNet-2012Top-1 accuracy: 55.06 -> 57.09Improved
Add momentum and weight decay to naive DessiLBI (ablation)AlexNet · ImageNet-2012Top-5 accuracy: 77.69 -> 79.86Improved
Add weight decay to DessiLBI with momentum (ablation)ResNet-18 · ImageNet-2012Top-1 accuracy: 68.55 -> 70.55Improved
Add weight decay to DessiLBI with momentum (ablation)ResNet-18 · ImageNet-2012Top-5 accuracy: 87.85 -> 89.56Improved
Add momentum and weight decay to naive DessiLBI (ablation)ResNet-18 · ImageNet-2012Top-1 accuracy: 65.26 -> 70.55Improved
Add momentum and weight decay to naive DessiLBI (ablation)ResNet-18 · ImageNet-2012Top-5 accuracy: 86.57 -> 89.56Improved

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