Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Auddy, Arnab, Cai, T. Tony, Chakraborty, Abhinav
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910506561830912
author Auddy, Arnab
Cai, T. Tony
Chakraborty, Abhinav
author_facet Auddy, Arnab
Cai, T. Tony
Chakraborty, Abhinav
contents This paper considers minimax and adaptive transfer learning for nonparametric classification under the posterior drift model with distributed differential privacy constraints. Our study is conducted within a heterogeneous framework, encompassing diverse sample sizes, varying privacy parameters, and data heterogeneity across different servers. We first establish the minimax misclassification rate, precisely characterizing the effects of privacy constraints, source samples, and target samples on classification accuracy. The results reveal interesting phase transition phenomena and highlight the intricate trade-offs between preserving privacy and achieving classification accuracy. We then develop a data-driven adaptive classifier that achieves the optimal rate within a logarithmic factor across a large collection of parameter spaces while satisfying the same set of differential privacy constraints. Simulation studies and real-world data applications further elucidate the theoretical analysis with numerical results.
format Preprint
id arxiv_https___arxiv_org_abs_2406_20088
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraints
Auddy, Arnab
Cai, T. Tony
Chakraborty, Abhinav
Statistics Theory
Methodology
Machine Learning
62G08, 62G20
This paper considers minimax and adaptive transfer learning for nonparametric classification under the posterior drift model with distributed differential privacy constraints. Our study is conducted within a heterogeneous framework, encompassing diverse sample sizes, varying privacy parameters, and data heterogeneity across different servers. We first establish the minimax misclassification rate, precisely characterizing the effects of privacy constraints, source samples, and target samples on classification accuracy. The results reveal interesting phase transition phenomena and highlight the intricate trade-offs between preserving privacy and achieving classification accuracy. We then develop a data-driven adaptive classifier that achieves the optimal rate within a logarithmic factor across a large collection of parameter spaces while satisfying the same set of differential privacy constraints. Simulation studies and real-world data applications further elucidate the theoretical analysis with numerical results.
title Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraints
topic Statistics Theory
Methodology
Machine Learning
62G08, 62G20
url https://arxiv.org/abs/2406.20088