AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differentially Private Empirical Risk Minimization under the Fairness Lens

Cuong Tran, My H Dinh, Ferdinando Fioretto

NeurIPS 2021 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 12 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 gradient-disparity and decision-boundary-proximity penalties during DP-SGDDP-SGD on Bank · Bankexcessive risk gapImproved
Add gradient-disparity and decision-boundary-proximity penalties during DP-SGDDP-SGD on Bank · Bankexcessive riskImproved
Increase the input norms of a groupDP-SGD · Several datasetsexcessive riskHurt
Increase the group's Hessian traceDP-SGD noise addition · Group-level analysisexcessive riskHurt
Increase the group's Hessian trace relative to the populationOutput perturbation · Group-level analysisexcessive risk gapHurt
Use equal average input norms across groupsOutput perturbation with L2 loss · Group-level analysisexcessive risk gapImproved
Increase the DP-SGD clipping boundDP-SGD · Bankgradient norm after clippingImproved
Increase the clipping bound enough for noise addition to dominate clippingDP-SGD · Group-level analysisnoise contribution to excessive riskImproved

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