AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning

Christopher A. Choquette-Choo, Hugh Brendan McMahan, J Keith Rush, Abhradeep Guha Thakurta

ICML 2023 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 6 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
Optimize the factorization directly for (k,b)=(20,100) multi-epoch participation rather than use the single-epoch MF baselineMatrix factorization mechanism · StackOverflow next-word prediction at ε=8.84accuracy: 24.11% -> 24.94%Improved
Optimize the factorization directly for multi-epoch participationMatrix factorization mechanism · StackOverflow next-word predictionprivacy-accuracy tradeoff: 24.94% at ε=8.84; 24.86% at ε=21.0Improved
Optimize the factorization directly for multi-epoch participationMatrix factorization mechanism · StackOverflow next-word predictionaccuracy: 25.25%Improved
Add a multi-epoch-optimized factorization instead of using the un-stamped single-epoch MF mechanismMF mechanism · CIFAR10 prefix-sum workload, (k,b)=(20,100)loss: 1.6e6 -> 6.5e5Improved
Stamp the single-epoch MF mechanism using n=1000 blocks ×2 (ablation)MF (k=1,n=2000) · CIFAR10 prefix-sum workload, (k,b)=(20,100)loss: 1.6e6 -> 1.37e6Improved
Stamp the multi-epoch MF mechanism as n=1000 blocks ×2 rather than use one n=2000 block (ablation)MF (k=20,n=2000) · CIFAR10 prefix-sum workload, (k,b)=(20,100)loss: 6.5e5 -> 8.8e5Hurt
Stamp the multi-epoch MF mechanism as n=500 blocks ×4 (ablation)MF (k=20,n=2000) · CIFAR10 prefix-sum workload, (k,b)=(20,100)loss: 6.5e5 -> 1.2e6Hurt
Stamp the single-epoch MF mechanism as n=100 blocks ×20 (ablation)MF (k=1,n=2000) · CIFAR10 prefix-sum workload, (k,b)=(20,100)loss: 1.6e6 -> 2.5e6Hurt
Stamp the Online Honaker mechanism as n=200 blocks ×10 rather than use n=2000 (ablation)Online Honaker · CIFAR10 prefix-sum workload, (k,b)=(20,100)loss: 5.8e6 -> 2.0e6Improved
Stamp the Optimal Decoder Honaker mechanism as n=400 blocks ×5 rather than use n=2000 (ablation)Optimal Decoder Honaker · CIFAR10 prefix-sum workload, (k,b)=(20,100)loss: 2.4e6 -> 1.2e6Improved
Remove noise contributions from virtual tree steps (ablation)Online Honaker tree-completion mechanism · CIFAR10 image classificationaccuracyImproved
Encode momentum and cooldown in the query matrix rather than apply them as post-processing (ablation)StackOverflow language-model training · StackOverflow next-word predictionaccuracyImproved

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