Kommunikationseffizientes verteiltes Lernen mit nachweislichen Robustheits- und Datenschutzgarantien
Year: 2025
Type: dissertation
Abstract: Distributed learning enables scalable machine learning across multiple devices, overcoming computational and privacy limitations in centralized approaches. This dissertation lays the foundation for a unified approach to communication efficiency, robustness, and data privacy in distributed learning. We consider federated learning orchestrated by a central entity, decentralized learning without central coordination, and outsourced computation on centrally stored data.
Author: Egger, Maximilian
Institution: Technical University of Munich
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7115610779
