AI Paper Atlas

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

Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization

Zijie Zhang, Yang Zhou, Xin Zhao, Tianshi Che, Lingjuan Lyu

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 2 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 PCMU instead of Fisher/NTK/SISA/DeltaGrad etc. for accuracy closeness to RetrainPCMU · Fashion-MNIST and CIFAR-10accuracy: 64.33 vs 64.31 (Retrain) on CIFAR-10 10%Improved
Replace baselines with PCMU, absolute accuracy difference to RetrainPCMU · Fashion-MNISTabsolute accuracy difference: at least 5.56%Improved
Replace baselines with PCMU, absolute accuracy difference to RetrainPCMU · CIFAR-10absolute accuracy difference: at least 15.17%Improved
Replace baselines with PCMU, absolute error difference to RetrainPCMU · Fashion-MNISTabsolute error difference: at least 13.73%Improved
Replace baselines with PCMU, absolute error difference to RetrainPCMU · CIFAR-10absolute error difference: at least 16.01%Improved
Use exact PCMU instead of variant PCMU-N (ablation)PCMU · Fashion-MNIST and CIFAR-10accuracy and errors vs RetrainImproved
Increase data removal ratio from 10% to 20%PCMU · Fashion-MNISTaccuracy: 88.34 -> 88.34No clear effect
Increase data removal ratio from 10% to 20%PCMU · CIFAR-10accuracy: 64.33 -> 64.33No clear effect
Vary data removal ratio from 5% to 20%PCMU · Fashion-MNIST, CIFAR-10, SVHNaccuracyNo clear effect
Increase Gaussian smoothing sigma from 0.025 to 0.3 (ablation)PCMU · Fashion-MNIST, CIFAR-10accuracyMixed
Use PCMU one-time unlearning instead of sequential DeltaGrad on runtimePCMU · Fashion-MNISTtotal runtime (s): 802 vs 694Hurt
Use PCMU instead of Fisher on runtimePCMU · Fashion-MNIST 10%total runtime (s): 2,686 -> 802Improved

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