AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

An Operator Theoretic View On Pruning Deep Neural Networks

William T Redman, MARIA FONOBEROVA, Ryan Mohr, Yannis Kevrekidis, Igor Mezic

ICLR 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 2 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 Koopman magnitude pruning instead of global magnitude pruningMnistNet · MNISTaccuracyNo clear effect
Use Koopman magnitude pruning instead of global magnitude pruningResNet-20 · CIFAR-10accuracyNo clear effect
Use Koopman magnitude pruning instead of global magnitude pruningMnistNet · MNIST, epochs 1 and 20accuracyNo clear effect
Use Koopman magnitude pruning instead of global magnitude pruningResNet-20 · CIFAR-10, epochs 1 and 20accuracyNo clear effect
Use global magnitude pruning instead of layer shuffle pruningResNet-20 · CIFAR-10, epoch 1accuracyHurt
Use Koopman magnitude pruning instead of layer shuffle pruningResNet-20 · CIFAR-10, epoch 1accuracyHurt
Use global magnitude pruning instead of layer shuffle pruningResNet-20 · CIFAR-10, epoch 20, compression below 16accuracyImproved
Use Koopman magnitude pruning instead of layer shuffle pruningResNet-20 · CIFAR-10, epoch 20, compression below 16accuracyImproved
Use global magnitude pruning instead of layer shuffle pruningMnistNet · MNIST, epoch 1, compression above 8accuracyImproved
Use Koopman magnitude pruning instead of layer shuffle pruningMnistNet · MNIST, epoch 1, compression above 8accuracyImproved
Use Koopman gradient pruning instead of just gradient pruningResNet-20 · CIFAR-10, epoch 20accuracyNo 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