# Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible

arXiv: https://arxiv.org/abs/1706.03316 · HTML: https://mlsanity.com/paper/1706.03316/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2017.

## Built on by (most cited first, 12 of 12)

- [Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging](https://mlsanity.com/paper/2206.05091/) (2022)
- [Differentially Private Decentralized Learning with Random Walks](https://mlsanity.com/paper/2402.07471/) (2024)
- [SoK: A Review of Differentially Private Linear Models For High-Dimensional Data](https://mlsanity.com/paper/2404.01141/) (2024)
- [Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model](https://mlsanity.com/paper/2310.07367/) (2023)
- [Topology-Based Reconstruction Prevention for Decentralised Learning](https://mlsanity.com/paper/2312.05248/) (2023)
- [Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy](https://mlsanity.com/paper/2410.18404/) (2024)
- [One-bit Submission for Locally Private Quasi-MLE: Its Asymptotic Normality and Limitation](https://mlsanity.com/paper/2202.07194/) (2022)
- [On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data](https://mlsanity.com/paper/2209.08319/) (2022)
- [Better Locally Private Sparse Estimation Given Multiple Samples Per User](https://mlsanity.com/paper/2408.04313/) (2024)
- [DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing](https://mlsanity.com/paper/2411.16121/) (2024)
- [Distributed Differentially Private Data Analytics via Secure Sketching](https://mlsanity.com/paper/2412.00497/) (2024)
- [Learning with Locally Private Examples by Inverse Weierstrass Private Stochastic Gradient Descent](https://mlsanity.com/paper/2602.16436/) (2026)

## Abstract (arXiv)

Non-interactive Local Differential Privacy (LDP) requires data analysts to collect data from users through noisy channel at once. In this paper, we extend the frontiers of Non-interactive LDP learning and estimation from several aspects. For learning with smooth generalized linear losses, we propose an approximate stochastic gradient oracle estimated from non-interactive LDP channel, using Chebyshev expansion. Combined with inexact gradient methods, we obtain an efficient algorithm with quasi-polynomial sample complexity bound. For the high-dimensional world, we discover that under ℓ2-norm assumption on data points, high-dimensional sparse linear regression and mean estimation can be achieved with logarithmic dependence on dimension, using random projection and approximate recovery. We also extend our methods to Kernel Ridge Regression. Our work is the first one that makes learning and estimation possible for a broad range of learning tasks under non-interactive LDP model.