The Dual² approach produces iD2A and MiD2A gradient methods that achieve asymptotic convergence under milder conditions on the public function and linear rates with reduced communication and computation complexity.
Deep learning with differential privacy
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
EdgeDetect delivers 98% multi-class accuracy in federated intrusion detection with 32x gradient compression via median binarization and homomorphic encryption, cutting per-round communication from 450 MB to 14 MB.
citing papers explorer
-
Accelerated Decentralized Constraint-Coupled Optimization: A Dual$^2$ Approach
The Dual² approach produces iD2A and MiD2A gradient methods that achieve asymptotic convergence under milder conditions on the public function and linear rates with reduced communication and computation complexity.
-
EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection
EdgeDetect delivers 98% multi-class accuracy in federated intrusion detection with 32x gradient compression via median binarization and homomorphic encryption, cutting per-round communication from 450 MB to 14 MB.