A differentially private particle-gradient algorithm generates continuous-time synthetic trajectories from one snapshot per person, but its headline recovery rate applies only to a non-private infinite-particle idealization.
Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics
A differentially private particle-gradient algorithm generates continuous-time synthetic trajectories from one snapshot per person, but its headline recovery rate applies only to a non-private infinite-particle idealization.