FiBeR adds a closed-form filter-aware correction A(ω)σ_w² to the second-moment term for temporally filtered DP gradients, improving adaptive optimization performance.
arXiv preprint arXiv:2011.11660 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
DP-SGD with expected or batch averaging (EASGM or ASGM) has weaker privacy guarantees than the standard subsampled Gaussian mechanism analysis, confirmed by theoretical re-analysis and audits of libraries including Opacus.
Federated learning matches centralized training performance for mental health detection from social media but differentially private federated learning causes large accuracy drops because noise distorts sparse but informative linguistic markers.
citing papers explorer
-
FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction
FiBeR adds a closed-form filter-aware correction A(ω)σ_w² to the second-moment term for temporally filtered DP gradients, improving adaptive optimization performance.
-
Rethinking the Security of DP-SGD: A Corrected Analysis of Differentially Private Machine Learning
DP-SGD with expected or batch averaging (EASGM or ASGM) has weaker privacy guarantees than the standard subsampled Gaussian mechanism analysis, confirmed by theoretical re-analysis and audits of libraries including Opacus.
-
FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
Federated learning matches centralized training performance for mental health detection from social media but differentially private federated learning causes large accuracy drops because noise distorts sparse but informative linguistic markers.