Distributed robust estimation and inference with contaminated data
Abstract
of observations from an arbitrary distribution. In a linear model setting, we develop a communication-efficient M-estimator that achieves the optimal convergence rate of centralized data. For robust inference, we introduce a distributed multiplier bootstrap method that requires no additional communication post-estimation while maintaining efficiency. To handle high contamination proportions, we present a debiasing procedure to mitigate bias. Extensive simulations demonstrate the robustness and scalability of our methods across diverse contamination scenarios.
Fields of Study & Subjects
Advanced Statistical Methods and Models
Distributed Sensor Networks and Detection Algorithms
Adversarial Robustness in Machine Learning
Publication details
- Journal / source
- Electronic Journal of Statistics
- Publisher
- Institute of Mathematical Statistics
- Volume
- 20
- Issue
- 1
- Pages
- 261–323
- Publication date
- 1 January 2026
- Language
- EN