AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

A Unified Fast Gradient Clipping Framework for DP-SGD

Weiwei Kong, Andres Munoz medina

NeurIPS 2023 · Optimization › Implicit bias and generalization · approach: SGD noise and flat minima · 1 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 Adjoint instead of ghost clipping for gradient-norm computationDP-SGD fully-connected layer · bias dimension m and output dimension q sweepruntime and memoryImproved
use Adjoint instead of ghost clipping for gradient-norm computationDP-SGD embedding layer · query size q and vocabulary size r sweepruntime and memoryImproved
use Adjoint instead of naive per-example gradientsDP-SGD small BERT · batch sizes 100 to 1600runtime and peak memoryImproved
increase bias dimension mGhostClip · fully-connected layerruntimeHurt
increase query size qGhostClip · embedding layermemoryHurt

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