AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference

Jasper Tan, Blake Mason, Hamid Javadi, Richard Baraniuk

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Double descent and overfitting · 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
increase number of parameters p (gamma above 2)minimum-norm least squares · Gaussian linear regressionmembership advantageHurt
make model only slightly overparameterized (gamma at or below 2)minimum-norm least squares · Gaussian linear regressionmembership advantageImproved
add ridge regularization in highly overparameterized regimeridge regression · Gaussian linear regressionmembership advantageHurt
reduce number of features (feature reduction)linear regression · Gaussian linear regressionmembership advantageImproved
add Gaussian noise to outputs of non-member querieslinear regression with all features · Gaussian linear regressionmembership advantageImproved
compare feature reduction to noise addition on privacy-utility trade-offlinear regression · Gaussian linear regressionmembership advantageNo clear effect
increase number of frequency components pinterpolating regressor · noise-free time-series regressionmembership advantageHurt
increase number of parameters in highly overparameterized regimerandom ReLU features regression · random ReLU featuresmembership advantageHurt

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