No article text was recorded for this version.
gradient difference clipping
Version 1 of 117 papers26 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
- Blog: Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
- Blog: Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
- Blog: Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
- Blog: Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee
- Blog: Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent
- Blog: Byzantine-Robust Decentralized Stochastic Optimization with Stochastic Gradient Noise-Independent Learning Error
- Blog: Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks
- Blog: Stochastic Adversarial Noise in the "Black Box" Optimization Problem
- Blog: Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
- Blog: Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences
- Blog: Byzantine-Robust Distributed Online Learning: Taming Adversarial Participants in An Adversarial Environment
- Blog: Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums
- Blog: Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums
- Blog: Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation
- Blog: Accelerating Byzantine-Robust Distributed Learning with Compressed Communication via Double Momentum and Variance Reduction
- Blog: Byzantine-robust variance-reduced federated learning over distributed non-i.i.d. data
History & citation
Current · Permanent link
- This direction split from robust gradient aggregation (59% overlap)
- This direction split from Variance Reduction for Byzantine Robustness (71% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_gradient_difference_clipping_110fafc1,
title = {gradient difference clipping},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-difference-clipping/rdr_110fafc1696d4fd2b9ef7c7546f455c7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_gradient_difference_clipping_110fafc1_v1,
title = {gradient difference clipping},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-difference-clipping/rdr_110fafc1696d4fd2b9ef7c7546f455c7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}