AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning

Yong Lin, Chen Liu, Chenlu Ye, Qing Lian, Yuan Yao, Tong Zhang

JMLR 2025 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 9 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 clipping of maximum uncertainty in the sampling ratio (COPS-clip) (ablation)COPS-vanilla · CIFAR10, CIFARBinary, CIFAR10-N coreset selection and active learningtest accuracyImproved
use vanilla uncertainty sampling instead of uniform samplinguniform sampling · CIFARBinary-600-WithYtest accuracy (%): 88.31 -> 75.26Hurt
add clipping of maximum uncertainty (COPS-clip) under label corruption in the low-density region, threshold 3 or 10 times the minimum uncertainty (ablation)COPS-vanilla on linear simulation · 2-D logistic simulation, corruption zeta(x1) = -3parameter error and regret lossImproved
increase corruption of the low-density region (zeta from 0 to -3) (ablation)COPS-vanilla · 2-D logistic simulationparameter error and regret lossHurt
estimate uncertainty with independently trained models of different initializations instead of bootstrap (ablation)COPS · CIFAR10-8,000test accuracyImproved
estimate uncertainty with Monte Carlo dropout instead of different initializations (ablation)COPS · CIFAR10 coreset selection (WithY)test accuracyNo clear effect
use COPS instead of uniform sampling across ResNet56, MobileNetV2 and DenseNet121uniform sampling · CIFAR10 multiple architecturestest accuracyImproved
use COPS instead of uniform sampling on SVHN, Places365 subset and IMDBuniform sampling · SVHN, Places365 (subset), IMDBtest accuracyImproved

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