Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

Read original
arXiv·Cristina Butucea·Sep 4, 2026, 11:55 AM

Faster Learning under Relaxed Local Differential Privacy

Papers74

Under a relaxed local differential privacy formulation bounded by total variation distance (α-TV-LDP), this paper re-evaluates density estimation rates. By perturbing sensitive observations with symmetrized Gamma noise, the authors establish that deconvolution estimators over r-Sobolev spaces attain a pointwise convergence rate of (nα)^{-(2r-1)/(2r)}, narrowing the statistical gap toward the non-private minimax baseline. Applied to neural network estimation, the framework circumvents the iterative gradient corruption typical of DP-SGD, improving empirical estimation efficiency over standard Laplace mechanisms.

Why it's worth reading

It demonstrates that relaxing local differential privacy via total variation distance allows estimators to nearly match non-private minimax rates, offering an alternative to iterative DP-SGD noise addition.

Tags

Differential PrivacyLocal DPDensity EstimationNonparametric StatisticsMachine Learning TheoryDP-SGD

Score breakdown

  • Novelty76
  • Impact71
  • Practicality68
  • Credibility81
  • Timeliness72