AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Lottery Jackpots Exist in Pre-Trained Models

Yuxin Zhang, Mingbao Lin, Yunshan Zhong, Fei Chao, Rongrong Ji

TPAMI 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Lottery ticket discovery · 14 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 magnitude-based mask initialization (ablation)SR-popup · CIFAR-10 ResNet-32 90%top-1 accuracy: 94.01 -> 94.30Improved
add short restriction on weight swapping (ablation)SR-popup · CIFAR-10 ResNet-32 90%top-1 accuracy: 93.69 -> 94.30Improved
select swap pairs with largest expected loss drops instead of inverse (ablation)SR-popup · CIFAR-10 ResNet-32 90%top-1 accuracy: 93.13 -> 94.30Improved
select swap pairs with largest expected loss drops instead of random (ablation)SR-popup · CIFAR-10 ResNet-32 90%top-1 accuracy: 93.84 -> 94.30Improved
use declining swap schedule instead of constant (ablation)SR-popup · CIFAR-10 ResNet-32top-1 accuracy: 93.13 -> 93.51Improved
use declining swap schedule instead of inverse schedule (ablation)SR-popup · CIFAR-10 ResNet-32top-1 accuracy: 93.44 -> 93.51Improved
replace Edge-popup with SR-popup (30 search epochs)Pre-trained ResNet-50 · ImageNet 90%top-1 accuracy: 70.20 -> 72.61Improved
replace Edge-popup with SR-popup (60 search epochs)Pre-trained ResNet-50 · ImageNet 90%top-1 accuracy: 70.89 -> 73.04Improved
increase searching from 10 to 60 epochsJackpot · CIFAR-10 ResNet-32 90%top-1 accuracy: 94.03 -> 94.43Improved
increase searching from 100 to 1000 epochsJackpot · CIFAR-10 ResNet-32 90%top-1 accuracy: 94.41 -> 94.43No clear effect
fine-tune weights after searching maskLottery jackpot · CIFAR-10 ResNet-32top-1 accuracyNo clear effect
prune VGGNet-19 with jackpot instead of denseJackpot 30 epochs · CIFAR-100 90%top-1 accuracy: 74.16 -> 74.63Improved

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