AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differentially Private Regression and Classification with Sparse Gaussian Processes

Michael Thomas Smith, Mauricio A. Alvarez, Neil D. Lawrence

JMLR 2021 · Federated learning and privacy › Differential privacy · approach: Private online and user-level learning · 3 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 sparse inducing-input approximation to DP cloakingDP GP regression · !Kung 1d (DP eps=1)RMSE (cm): 13.3 -> 9.9Improved
add sparse inducing-input approximation to DP cloakingDP GP regression · !Kung 2d (DP eps=1)RMSE (cm): 17.2 -> 10.2Improved
add variable lengthscale to DP cloakingDP GP regression · !Kung 1d (DP eps=1)RMSE (cm): 13.3 -> 12.8No clear effect
add variable lengthscale to DP cloakingDP GP regression · !Kung 2d (DP eps=1)RMSE (cm): 17.2 -> 16.3No clear effect
add weight as a second input to standard DP cloakingDP GP regression · !Kung (DP eps=1)RMSE (cm): 13.3 -> 17.2Hurt
add sparse approximation to GP without DPGP regression · !Kung 1d (no DP)RMSE (cm): 7.1 -> 7.7Hurt
add sparse approximation to GP without DPGP regression · !Kung 2d (no DP)RMSE (cm): 5.2 -> 7.7Hurt
add a second Laplace optimisation iteration with split privacy budget (ablation)DP GP classification · 2D stripe classificationaccuracy (%): 69% to 51%Hurt
use fewer inducing inputs and longer lengthscale (ablation)DP sparse GP classifier · MNIST low/high (15x15, 256 train)accuracyImproved
select hyperparameters with exponential mechanism instead of random choiceDP GP regression hyperparameters · !Kung 1d (80 configurations)expected RMSE (cm): 153.81 -> 19.02Improved
increase privacy (smaller epsilon) when selecting lengthscale (ablation)DP GP hyperparameter selection · !Kung 1dselected lengthscaleMixed

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