AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?

Jetze Schuurmans, kim batselier, Julian Kooij

ICLR 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 0 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 relative weight approximation error to choose among tensor-decomposition optionsTD-compressed GaripovNet and ResNet-18 · CIFAR-10; Fashion-MNISTKendall's tau correlation with classification errorImproved
Measure approximation error on output features instead of weights (ablation)TD-compressed CNNs · CIFAR-10; Fashion-MNISTKendall's tau correlation with classification errorNo clear effect
Use relative rather than absolute weight error (ablation)TD-compressed ResNet-18 · CIFAR-10Kendall's tau correlation with classification errorImproved
Compare choices at higher rather than lower compression levels (ablation)TD-compressed GaripovNet and ResNet-18 · CIFAR-10; Fashion-MNISTKendall's tau correlation with classification errorImproved
Compare choices at only 10% or 25% compression (ablation)TD-compressed GaripovNet and ResNet-18 · CIFAR-10; Fashion-MNISTKendall's tau correlation with classification errorHurt
Fine-tune the decomposed model after compression (ablation)TD-compressed GaripovNet · CIFAR-10; Fashion-MNISTKendall's tau correlation with performance errorHurt
Fine-tune the decomposed model after compression (ablation)TD-compressed ResNet-18 · CIFAR-10Kendall's tau correlation with performance errorNo clear effect
Compare layers while fixing decomposition method and compression level (ablation)TD-compressed CNNs · CIFAR-10; Fashion-MNISTKendall's tau correlation with performance errorHurt
Compare decomposition methods for a fixed layer (ablation)TD-compressed CNNs · CIFAR-10; Fashion-MNISTKendall's tau correlation with performance errorImproved
Fine-tune after comparing decomposition methods (ablation)TD-compressed GaripovNet · CIFAR-10; Fashion-MNISTKendall's tau correlation with performance errorHurt

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