AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers

Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Jian Tang, Wujie Wen, Makan Fardad, Yanzhi Wang

ECCV 2018 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 494 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
replace iterative prune-and-retrain with ADMM pruningLeNet-300-100 · MNISTweights remaining (%): 8% -> 4.37%Improved
replace iterative prune-and-retrain with ADMM pruningLeNet-5 · MNISTweights remaining (%): 8% -> 1.4%Improved
replace iterative prune-and-retrain with ADMM pruningAlexNet · ImageNet ILSVRC-2012weights remaining (%): 11% -> 4.76%Improved
target conv layers more aggressively using ADMM, keeping fc ratios as in prior workAlexNet · ImageNet ILSVRC-2012conv1-5 weights remaining (%): 37.1% -> 7.46%Improved
run 25 ADMM iterations instead of 10 (ablation)ADMM pruning · ImageNet ILSVRC-2012weight reduction ratio: 15x -> 18.8xImproved
run 40 ADMM iterations instead of 25 (ablation)ADMM pruning · ImageNet ILSVRC-2012weight reduction ratio: 18.8x -> 21xImproved
run more ADMM iterations (10 to 40) (ablation)ADMM pruning · ImageNet ILSVRC-2012top-5 error (%): 19.8% -> 19.8%No clear effect

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