AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams

Serguei Denissov, Hugh Brendan McMahan, J Keith Rush, Adam Smith, Abhradeep Guha Thakurta

NeurIPS 2022 · Federated learning and privacy › Differential privacy · approach: Privacy accounting and mechanisms · 8 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
iterate the fixed-point mapping instead of prior algorithm or gradient descentoptimal prefix-sum factorization · 2048x2048 prefix-sum matrixtime to reach loss (minutes): over 80 minutes -> less than 3 minutesImproved
learning rate decay for the last 512 rounds (0.15x)matrix factorization mechanisms · StackOverflow next-word predictiontest accuracyImproved
linear learning rate cooldown from 1.0x to 0.05x over last 512 roundsmatrix factorization mechanisms · StackOverflow next-word predictiontest accuracyImproved
increase clients per round from 100 to 167cooldown mechanism · StackOverflow next-word predictiontest accuracy: 100 -> 167 clients/roundImproved
matrix factorization mechanisms with constant learning rate vs previous state of the artDP-FTRL · StackOverflow next-word predictiontest accuracyImproved

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