AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates

Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang

ICML 2021 · Federated learning and privacy › Differential privacy · approach: Local-DP and private estimation · 1 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 DPALS instead of DPFWPrivate matrix completion on MovieLens 10M-top400 · MovieLens 10M-top400RMSE: 7% to 11.6% relative improvementImproved
use adaptive rather than uniform sampling (ablation)DPALS · MovieLens 10M, ε = 10RMSE: 0.870 -> 0.854Improved
train ALS on subsampled rather than all movie data (ablation)Non-private ALS · MovieLens 10M, ε = 10RMSE: 0.785 -> 0.812Hurt
remove PSD projection (ablation)DPALS · MovieLens 10M, ε = 10RMSEHurt
use adaptive rather than uniform sampling (ablation)Non-private ALS · MovieLens 10M, ε = 10RMSENo clear effect
replace DPFW with DPALSPrivate matrix completion · Synthetic data, ε = 1RMSE: DPFW RMSE equal to 1; DPALS has a lower RMSEImproved
replace DPFW with DPALSPrivate matrix completion · Synthetic data, n = 50Krelative RMSE improvement: at least 7-foldImproved
use DPALS instead of DPFWPrivate matrix completion · Theoretical sample complexity for target relative error ζusers required: DPALS: n\geq \frac{C m}{\zeta\cdot \varepsilon}; DPFW: n\geq \frac{C m^{5/4}}{\zeta^5\cdot \varepsilon}Improved
use adaptive sampling to favor rare itemsDPALS · MovieLens 20MRecall@kImproved

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