PLRV-O replaces Gaussian noise in DP-SGD with a randomized-scale Laplace distribution and claims large accuracy gains at epsilon under 1, but the privacy accounting likely underestimates the true privacy loss due to shared subsampling across model parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
PLRV-O replaces Gaussian noise in DP-SGD with a randomized-scale Laplace distribution and claims large accuracy gains at epsilon under 1, but the privacy accounting likely underestimates the true privacy loss due to shared subsampling across model parameters.