AI Paper Atlas

Research map / Optimization / Distributed and compressed

High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers

Wenyu Liu, Tianqiang Huang, Pengfei Zhang, Zong Ke, Minghui Min, Puning Zhao

AAAI 2026 · Optimization › Distributed and compressed · approach: Byzantine-robust learning · 17 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 semi-verified mean estimation aggregator instead of Zeno / distance filteringrobust distributed GD · Synthetic linear regression, d=20, 80% Byzantineroot regression lossNo clear effect
use the semi-verified mean estimation aggregator instead of Zeno / distance filteringrobust distributed GD · Synthetic linear regression, d=50, 80% Byzantineroot regression lossImproved
use the semi-verified mean estimation aggregatorrobust distributed GD · Synthetic linear regression, d=100, 80% Byzantineroot regression lossImproved
use the aggregator with only 20% Byzantine workersrobust distributed GD · Synthetic linear regression, 20% Byzantineroot regression lossNo clear effect
use the aggregator with 80% Byzantine workersrobust distributed GD · MNIST, 1-hidden-layer MLProot regression lossImproved
use the aggregator with 20% Byzantine workersrobust distributed GD · MNIST, 1-hidden-layer MLProot regression lossNo clear effect
use Zeno score selection instead of distance-based filteringrobust distributed GD · MNIST, 1-hidden-layer MLProot regression lossImproved

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