AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Weightless: Lossy weight encoding for deep neural network compression

Brandon Reagan, Udit Gupta, Bob Adolf, Michael Mitzenmacher, Alexander Rush, Gu-Yeon Wei, David Brooks

ICML 2018 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 32 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
Replace CSR/Huffman encoding with Bloomier-filter encoding and arithmetic codingPruned and clustered DNN weights · LeNet5 FC-0, DNS (MNIST)compression factor: 333× vs 224×Improved
Replace CSR/Huffman encoding with Bloomier-filter encoding and arithmetic codingPruned and clustered DNN weights · VGG-16 FC-1 (ImageNet)compression factor: 85.8× vs 88.4×Hurt
Use dynamic network surgery pruning instead of magnitude pruning (ablation)Weightless · LeNet5 FC-0 (MNIST)compression factor: 74.2× -> 496×Improved
Use dynamic network surgery pruning instead of magnitude pruning (ablation)Weightless · LeNet-300-100 FC-0 (MNIST)compression factor: 60.1× -> 174×Improved
Increase sparsity through stronger pruning (ablation)Weightless encoding · LeNet5 FC-0 (MNIST)compression factorImproved
Retrain subsequent layers around deterministic Bloomier-filter false positivesWeightless · VGG-16 FC-0 (ImageNet)top-1 accuracy: +2.0 percentage pointsImproved
Use Weightless rather than lossless Deep Compression after simplificationPruned and clustered models · LeNet-300-100, LeNet5, and VGG-16test errorNo clear effect
Apply arithmetic coding to Bloomier-filter tables (ablation)Weightless · VGG-16 FC-1 (ImageNet)compression factor: 74.6× -> 85.8×; baseline 71.2× -> 88.4×Hurt

Later papers that compared with this method

1 later accepted paper reports Weightless as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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