AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Pruning Randomly Initialized Neural Networks with Iterative Randomization

Daiki Chijiwa, Shin'ya Yamaguchi, Yasutoshi Ida, Kenji Umakoshi, Tomohiro INOUE

NeurIPS 2021 · Architectures and efficiency › Pruning and efficient tuning · approach: Lottery ticket discovery · 5 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
Add iterative partial randomization of pruned weights to edge-popupConv6 · CIFAR-10 test, ρ=0.25, SCaccuracy: 70.35 ± 1.16 -> 75.16 ± 0.23Improved
Add iterative partial randomization of pruned weights to edge-popupResNet18 · CIFAR-10 test, ρ=0.25, SCaccuracy: 84.23 ± 0.33 -> 86.09 ± 0.24Improved
Add iterative randomization during pruningResNet34 · ImageNet validation, 70% sparsityTop-1 accuracy: 62.14 -> 65.86Improved
Add iterative randomization during pruningResNet18 · CIFAR-10 test, p=0.99, SCaccuracy: 75.21 ± 2.71 -> 76.31 ± 2.56No clear effect
Use IMP with 3 retraining instead of pruning-only IteRandVGG11 · CIFAR-10, p=0.5accuracy: 88.46 ± 0.22 -> 91.47 ± 0.15Improved
Use partial randomization with r=0.1 rather than the other tested rates (ablation)CNNs · CIFAR-10 validationaccuracyImproved
Vary K_per; avoid very frequent randomization and periods so long that randomization nearly disappears (ablation)IteRand · CIFAR-10 validation, Conv6/ResNet18/ResNet34accuracyMixed
Increase r and adjust K_per to preserve the approximate randomization rate (ablation)IteRand · CIFAR-10 test, ResNet18accuracyNo clear effect
Increase width factor ρ (ablation)IteRand and edge-popup · CIFAR-10, Conv6/ResNet18/ResNet34accuracyImproved
Use IteRand instead of edge-popup at matched widthResNet18, KU · CIFAR-10 test, ρ=0.5accuracy: 88.45± 0.53 -> 89.96± 0.06Improved
Add iterative randomization during pruningLSTM · IMDB testaccuracy: 88.16 ± 0.12 % -> 88.44 ± 0.28 %Improved

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