A differentially private gradient-tracking algorithm for distributed stochastic optimization on directed graphs uses subsampling schemes to achieve convergence for nonconvex objectives with finite privacy budget.
A(DP) 2SGD: asynchronous decentral- ized parallel stochastic gradient descent with differential privacy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Differentially Private Gradient-Tracking-Based Distributed Stochastic Optimization over Directed Graphs
A differentially private gradient-tracking algorithm for distributed stochastic optimization on directed graphs uses subsampling schemes to achieve convergence for nonconvex objectives with finite privacy budget.