AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent

Rishav Chourasia, Jiayuan Ye, Reza Shokri

NeurIPS 2021 · Optimization › Nonconvex and smooth optimization · approach: Langevin sampling for nonconvex problems · 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
Use the privacy-dynamics RDP bound instead of composition-based privacy accountingNoisy GD · Noisy GD training over K iterationsRDP privacy loss: composition-based bound grows linearly with K; proposed bound is proportional to (1-e^{-\lambda\etaK/2})Improved
Require smoothness and strong convexity, with an initialization that satisfies the stated Gaussian conditionNoisy GD privacy guarantee · Noisy GD on neighboring datasetsRDP privacy loss: \varepsilon = \frac{\alpha S_g^2}{\lambda \sigma^2n^2}(1-e^{-\lambda\etaK/2})Improved
Apply the analysis to squared-norm loss and use its tighter LSI constantNoisy GD · Squared-norm lossRDP privacy bound: \frac{\alpha S_g^2 }{(2-\eta)\sigma^2n^2}(1-e^{-\frac{2-\eta}{2}\etaK})Improved
Use Noisy GD rather than Noisy SGD for the stated strongly convex utility regimePrivacy-preserving ERM · Lipschitz, smooth, strongly convex ERMgradient complexity: a factor of $n/{\log n}$Improved

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