On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data
Not on the map. Why?
Abstract (arXiv)
In this paper, we study the problem of PAC learning halfspaces in the non-interactive local differential privacy model (NLDP). To breach the barrier of exponential sample complexity, previous results studied a relaxed setting where the server has access to some additional public but unlabeled data. We continue in this direction. Specifically, we consider the problem under the standard setting instead of the large margin setting studied before. Under different mild assumptions on the underlying data distribution, we propose two approaches that are based on the Massart noise model and self-supervised learning and show that it is possible to achieve sample complexities that are only linear in the dimension and polynomial in other terms for both private and public data, which significantly improve the previous results. Our methods could also be used for other private PAC learning problems.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 17 Sep 2022.
Builds on
16 of 35 references.
References · 16
- 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
- 2017A Hitting Time Analysis of Stochastic Gradient Langevin Dynamicscited by 70
- 2020An Equivalence Between Private Classification and Online Predictioncited by 63
- 2020Learning Halfspaces with Massart Noise Under Structured Distributionscited by 45
- 2017Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12cited by 42
- 2015Efficient Learning of Linear Separators under Bounded Noisecited by 36
- 2017Heavy Hitters and the Structure of Local Privacycited by 20
- 2018Empirical Risk Minimization in Non-interactive Local Differential Privacy: Efficiency and High Dimensional Casecited by 19
- 2021Self-training Converts Weak Learners to Strong Learners in Mixture Modelscited by 19
- 2020Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacycited by 15
- 2019Private Center Points and Learning of Halfspacescited by 13
- 2017Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possiblecited by 12
4 more
- 2019Efficient Private Algorithms for Learning Large-Margin Halfspacescited by 12
- 2019Interaction is necessary for distributed learning with privacy or communication constraintscited by 8
- 2018Locally Private Learning without Interaction Requires Separationcited by 7
- 2018Noninteractive Locally Private Learning of Linear Models via Polynomial Approximationscited by 7
Built on by
Citing papers per year: 2023: 1.
1 paper.