AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

PDP: Parameter-free Differentiable Pruning is All You Need

Minsik Cho, Saurabh Adya, Devang Naik

NeurIPS 2023 · 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
Add the PDP soft mask rather than using the same training configuration without it (ablation)PDP · ImageNet1k, ResNet50Top-1 accuracy (%): 73.1 -> 74.7Improved
Add the PDP soft mask rather than using the same training configuration without it (ablation)PDP · ImageNet1k, MobileNet-v1Top-1 accuracy (%): 66.8 -> 68.2Improved
Train for more epochs to match ACDC GPU cost (PDP-base+) (ablation)PDP-base · ImageNet1k, ResNet18, 85.5% sparsityTop-1 accuracy (%): 69.0 -> 69.5Improved
Train for more epochs to match ACDC GPU cost (PDP-base+) (ablation)PDP-base · ImageNet1k, ResNet50, 89.8% sparsityTop-1 accuracy (%): 74.7 -> 75.3Improved
Use STR's per-layer sparsity allocation with PDP (PDP-str) (ablation)PDP · ImageNet1k, ResNet18, 85.5% sparsityTop-1 accuracy (%): 69.0 -> 68.6Hurt
Use OptG's per-layer sparsity allocation with PDP (PDP-optg) (ablation)PDP · ImageNet1k, ResNet18, 85.5% sparsityTop-1 accuracy (%): 69.0 -> 68.5Hurt
Vary the mask temperature τ (ablation)PDP on MobileNet-v2 · ImageNet1kTop-1 accuracyMixed
Use PDP rather than LNM for 1:4 structured pruningResNet18 · ImageNet1k, 1:4 pruningTop-1 accuracy (%): 65.1 -> 68.7Improved
Use PDP rather than LNM for 2:4 structured pruningResNet50 · ImageNet1k, 2:4 pruningTop-1 accuracy (%): 74.6 -> 75.9Improved
Apply PDP to channel pruningResNet50 · ImageNet1k, channel pruningTop-1 accuracy (%): 75.3 -> 75.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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