Fundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated Learning

arXiv:2610.25743 · cs.IT, cs.CR, cs.LG, math.IT · Submitted 2026-10-19 · Read on arXiv

cs.IT, cs.CR, cs.LG, math.IT

Submitted: 2026-10-19

Updated: 2026-10-19

Comments: The abstract was shortened to meet arXiv's requirements. The full version is included in the manuscript

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Federated Learning — 1× in this paper · explained in 17 episodes

Related papers

• Task-Sufficient Contraction: Source Selection for Machine Information Interfaces
• Language Modeling is Monotone Compression
• Clipped Affine Policy: Low-Complexity Near-Optimal Online Power Control for Energy Harvesting Communications over Fading Channels
• Discrepancy for Random Linear Codes
• A New Approach to Code Smoothing Bounds
• Contextual Memory-Enhanced Source Coding for Low-SNR Communications