mlsanityData to 14 Oct 2026

Optimal Locally Private Nonparametric Classification with Public Data

arXiv 2311.11369 ↗First posted 19 Nov 2023stat.ML cs.CR cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

In this work, we investigate the problem of public data assisted non-interactive Local Differentially Private (LDP) learning with a focus on non-parametric classification. Under the posterior drift assumption, we for the first time derive the mini-max optimal convergence rate with LDP constraint. Then, we present a novel approach, the locally differentially private classification tree, which attains the mini-max optimal convergence rate. Furthermore, we design a data-driven pruning procedure that avoids parameter tuning and provides a fast converging estimator. Comprehensive experiments conducted on synthetic and real data sets show the superior performance of our proposed methods. Both our theoretical and experimental findings demonstrate the effectiveness of public data compared to private data, which leads to practical suggestions for prioritizing non-private data collection.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 8 of its 78 references that are in the map. First posted on arXiv 19 Nov 2023.

Builds on

8 of 78 references.

References · 8

  1. 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
  2. 2022Position: Considerations for Differentially Private Learning with Large-Scale Public Pretrainingcited by 88
  3. 2020Training Production Language Models without Memorizing User Datacited by 68
  4. 2017Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12cited by 43
  5. 2023Selective Pre-training for Private Fine-tuningcited by 23
  6. 2023Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distancecited by 16
  7. 2019Classification under local differential privacycited by 9
  8. 2023Optimal Differentially Private Model Training with Public Datacited by 9

Built on by

Cited by year (2026 to 14 Oct)

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

7 papers.

  1. 2024Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraintscited by 5
  2. 2024Locally Private Estimation with Public Featurescited by 3
  3. 2025Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via f-Differential Privacycited by 3
  4. 2024Better Locally Private Sparse Estimation Given Multiple Samples Per Usercited by 1
  5. 2025PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structurecited 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