AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

BayesTune: Bayesian Sparse Deep Model Fine-tuning

Minyoung Kim, Timothy Hospedales

NeurIPS 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 1 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 SGLD posterior mean instead of MAP for scale variables (ablation)BayesTune · NLP 7-task averageaverage score: 76.30 -> 78.12Improved
use SGLD posterior mean instead of MAP (ablation)BayesTune · CBaccuracy: 86.71 -> 91.25Improved
use SGLD posterior mean instead of MAP (ablation)BayesTune · CoLAscore: 58.55 -> 60.85Improved
Bayesian posterior (BayesTune stage II) instead of two-stage L1-SP selection (ablation)sparse fine-tuning · NLP 7-task averageaverage score: 72.64 -> 78.12Improved
apply sparse selection (stage II) after L1-SP training instead of using L1-SP alone (ablation)L1-SP · NLP 7-task averageaverage score: 64.12 -> 72.64Improved
BayesTune vs SAM sparse fine-tuningRoBERTa-base · NLP 7-task averageaverage score: 77.12 -> 78.12Improved
BayesTune vs random selection (Random)RoBERTa-base · NLP 7-task averageaverage score: 74.55 -> 78.12Improved
increase sparsity level p from 0.005 to 0.5 (ablation)BayesTune · NLP average test accuracyaccuracyHurt
vary sparsity level p among 0.01 to 0.1 (ablation)BayesTune · NLP average test accuracyaccuracyNo clear effect
place scale variables on ViT backbone parameters instead of extra modules (ablation)BayesTune · VTAB-1KaccuracyHurt
sparser adapter updates (smaller p) on Sun397, CIFAR100, DTD, Retinopathy (ablation)BayesTune · VTAB-1KaccuracyImproved
denser adapter updates on DMLab, Camelyon, SVHN, dSpr-Loc (ablation)BayesTune · VTAB-1KaccuracyMixed

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