AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Towards Accelerated Model Training via Bayesian Data Selection

Zhijie Deng, Peng Cui, Jun Zhu

NeurIPS 2023 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 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 Bayesian generalization-loss-based online data selection instead of RHO-LOSSResNet18 training on CIFAR-100 · CIFAR-100epochs to reach 40.0% accuracy: 48 -> 32Improved
use Bayesian generalization-loss-based online data selection instead of RHO-LOSSResNet18 training on WebVision-200 · WebVision-200, ILSVRC12 validationfinal accuracy: 39% -> 56%Improved
replace the zero-shot predictor with the RHO-LOSS validation model (ablation)Proposed method · CIFAR-100epochs to reach 40.0% test accuracy: 32 -> 30Improved
replace the zero-shot predictor with the RHO-LOSS validation model (ablation)Proposed method · CIFAR-100final accuracy: 63% -> 63%No clear effect
use only the zero-shot predictor term (α=0) (ablation)Proposed method · CIFAR-100final accuracyHurt
increase α enough to downweight the zero-shot predictor term (ablation)Proposed method · CIFAR-100training speedHurt
vary the effective-data parameter n_e (ablation)Proposed method · CIFAR-100training performanceNo clear effect
use an appropriate CLIP softmax temperature τ (ablation)Proposed method · CIFAR-100training performanceImproved
use CLIP RN50 rather than the higher-zero-shot-accuracy ViT-B/16 predictor (ablation)Proposed method · CIFAR-100training speedupNo clear effect
replace the ResNet18 training backbone with a pretrained ViT-B/16 (ablation)Proposed method · WebVision-200training performanceImproved

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