AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Eliminating Solution Bias in Differentially Private Optimization

DONGRUN LI, YUN ZENG, Zibo Wei, Jiacheng Wei, Qinnan Zhang, Faguo Wu, Xiao Zhang, Zhiming Zheng

ICML 2026 · Federated learning and privacy › Differential privacy · approach: DP-SGD refinements

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 DP-C4 instead of DiceSGDDP optimizer · CIFAR-10 (eps=5)test accuracy (%): 60.24 -> 64.50Improved
use DP-C4 instead of DiceSGDDP optimizer · Mushroom (SVM, logistic regression, eps=1)test accuracy (%): 90.65 -> 96.98Improved
use DP-C4 instead of DiceSGDDP optimizer · GLUE SST-2 (eps=2)test accuracy (%): 78.71 -> 82.24Improved
use DP-C4 instead of DiceSGDDP optimizer · IMDb (eps=2)test accuracy (%): 78.19 -> 81.23Improved
use DP-C4 instead of DiceSGDDP optimizer · CIFAR-100 (eps=5)test accuracy (%): 40.73 -> 43.12Improved
use DP-C4 instead of DiceSGDDP optimizer · Mnist (eps=5)test accuracy (%): 97.02 -> 97.16No clear effect
use DP-C4 instead of DP-SGDDP optimizer · CIFAR-10 (eps=5)test accuracy (%): 53.05 -> 64.50Improved
use DP-SVRG variance reduction instead of DP-SGDDP optimizer · Mushroom (SVM, logistic regression, eps=1)test accuracy (%): 87.48 -> 77.13Hurt

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