ImprovDML is a decentralized SGD framework that uses resilient vector consensus aggregation and Gaussian noise, with concentrated geo-privacy analysis, achieving Byzantine resilience and a better privacy-accuracy trade-off than differential privacy.
Optimization methods for large-scale machine learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning
ImprovDML is a decentralized SGD framework that uses resilient vector consensus aggregation and Gaussian noise, with concentrated geo-privacy analysis, achieving Byzantine resilience and a better privacy-accuracy trade-off than differential privacy.