AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Rare Gems: Finding Lottery Tickets at Initialization

Kartik Sreenivasan, Jy-yong Sohn, Liu Yang, Matthew Grinde, Alliot Nagle, Hongyi Wang, Eric Xing, Kangwook Lee, Dimitris Papailiopoulos

NeurIPS 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Lottery ticket discovery · 10 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
prune scores globally instead of layer-wise (ablation)Edge-Popup · CIFAR-10 ResNet-20 0.59% sparsitypost-finetune acc (%): 24.47 -> 34.42Improved
add gradual pruning to global EP (ablation)Global EP · CIFAR-10 ResNet-20 0.59% sparsitypost-finetune acc (%): 34.42 -> 63.54Improved
add L2 score regularization to global gradual EP (ablation)Global EP with Gradual Pruning · CIFAR-10 ResNet-20 0.59% sparsitypost-finetune acc (%): 63.54 -> 63.72No clear effect
add L2 regularization to global gradual EP (ablation)Global EP with Gradual Pruning · CIFAR-10 ResNet-20 0.59% sparsitypre-finetune acc (%): 31.56 -> 19.67Hurt
run Gem-Miner 3000 epochs instead of 300 (prune every 150 epochs) (ablation)Gem-Miner · CIFAR-10 ResNet-20 1.4% sparsitypost-finetune accuracy (%): 77.89 -> 79.50Improved
use Gem-Miner at initialization instead of ProsPrpruning at initialization · CIFAR-10 ResNet-20post-finetune accuracy: 82.67% -> 83.4%Improved
Gem-Miner instead of IMP with warmupResNet-20 · CIFAR-10 1.4% sparsitypost-finetune accuracy (%): 74.52 -> 77.89Improved
Gem-Miner in dense regime (50% or 20% sparsity)Gem-Miner · CIFAR-10post-finetune accuracyHurt
Gem-Miner on Caltech-101 finetuning vs IMPResNet-50 · Caltech-101post-finetune accuracyHurt

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