mlsanityData to 14 Oct 2026

Classification under local differential privacy

arXiv 1912.04629 ↗First posted 10 Dec 2019math.ST stat.ME stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample that is universally consistent in Euclidean spaces. Under stronger assumptions, we establish the minimax rates of convergence of the excess risk and see that they are slower than in the case when the original sample is available.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 3.

9 papers.

  1. 2023Optimal Locally Private Nonparametric Classification with Public Datacited by 7
  2. 2024Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraintscited by 5
  3. 2023Private Statistical Estimation of Many Quantilescited by 3
  4. 2024Learning with User-Level Local Differential Privacycited by 3
  5. 2023On Rate-Optimal Partitioning Classification from Observable and from Privatised Datacited by 1
  6. 2025Locally Private Nonparametric Contextual Multi-armed Banditscited by 0
  7. 2026Classification Under Local Differential Privacy with Model Reversal and Model Averagingcited by 0
  8. 2026SLDP: Semi-Local Differential Privacy for Density-Adaptive Analyticscited by 0
  9. 2026On public and private binary classification with metric space valued predictorscited by 0