AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

What's Hidden in a Randomly Weighted Neural Network?

Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari

CVPR 2020 · Architectures and efficiency › Pruning and efficient tuning · approach: Pruning at initialization

Check 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 Signed Kaiming Constant rather than Kaiming Normal initialization (ablation)edge-popup · ImageNettop-1 accuracy: 61.71% -> 68.6% (ResNet-50); 66.15% -> 72.3% (ResNet-101); 67.95% -> 73.3% (Wide ResNet-50)Improved
Increase parent network width and depthedge-popup subnetworks with randomly weighted parent networks · CIFAR-10 and ImageNetaccuracyImproved
Increase parent network width while holding subnetwork parameter count fixed (ablation)edge-popup · CIFAR-10accuracyImproved
Choose a middle sparsity level rather than a value near 0% or 100% (ablation)edge-popup · CIFAR-10accuracyImproved
Use a scaled initialization with the additional sqrt(1/k) factor (ablation)edge-popup · ImageNettop-1 accuracyImproved
Use a scaled initialization with the additional sqrt(1/k) factor (ablation)edge-popup · CIFAR-10accuracyNo clear effect
Train the weights of the discovered subnetwork after finding it (ablation)edge-popup subnetworks · ImageNettop-1 accuracy: 73.5% vs 73.6% (ResNet-50, Kaiming Normal); 76.5% vs 76.8% (Wide ResNet-50, Kaiming Normal); 76.1% vs 76.1% (ResNet-101,No clear effect
Replace deterministic top-score edge selection with stochastic mask samplingedge-popup versus Zhou et al.'s supermask method · CIFAR-10 and ImageNetaccuracyHurt

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