Year: 2026
Type: preprint
Abstract: We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal is achieved through a local training approach, which reduces communication frequency. The second goal is achieved by perturbing gradients during local training, specifically through gradient clipping and additive noise. We prove that the resulting algorithm converges to a stationary point of the problem within a bounded distance. Additionally, we provide theoretical privacy guarantees within a differential privacy framework that ensure agents' training data cannot be inferred from the trained model shared over the network. We show the algorithm's superior performance on a classification task under the same privacy budget, compared with state-of-the-art methods.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Collaborative Research: SLES: Improving Safety by Synthesizing Interacting Model-based and Model-free Learning Approaches, High-confidence cooperation, control, and learning, NRI: Addressing Safe Interaction Between Autonomous and Human-Driven Vehicles, Collaborative Research: CPS: Medium: An Online Learning Framework for Socially Emerging Mixed Mobility
OpenAlex ID: W7150832338