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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use the semi-verified mean estimation aggregator instead of Zeno / distance filtering | robust distributed GD · Synthetic linear regression, d=20, 80% Byzantine | root regression loss | No clear effect |
| use the semi-verified mean estimation aggregator instead of Zeno / distance filtering | robust distributed GD · Synthetic linear regression, d=50, 80% Byzantine | root regression loss | Improved |
| use the semi-verified mean estimation aggregator | robust distributed GD · Synthetic linear regression, d=100, 80% Byzantine | root regression loss | Improved |
| use the aggregator with only 20% Byzantine workers | robust distributed GD · Synthetic linear regression, 20% Byzantine | root regression loss | No clear effect |
| use the aggregator with 80% Byzantine workers | robust distributed GD · MNIST, 1-hidden-layer MLP | root regression loss | Improved |
| use the aggregator with 20% Byzantine workers | robust distributed GD · MNIST, 1-hidden-layer MLP | root regression loss | No clear effect |
| use Zeno score selection instead of distance-based filtering | robust distributed GD · MNIST, 1-hidden-layer MLP | root regression loss | Improved |
Closest papers by meaning
- From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity (NeurIPS 2026 · similarity 0.87)
- On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning (ICML 2025 · similarity 0.87)
- Byzantine-Robust Decentralized Learning via Remove-then-Clip Aggregation (AAAI 2024 · similarity 0.85)
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients (NeurIPS 2025 · similarity 0.85)
- Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization (ICLR 2024 · similarity 0.85)
- Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences (NeurIPS 2024 · similarity 0.84)
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.
