Communication-Efficient Federated Online Decision-Making with Stateful Costs
Yiwei Liu, Luwei Yang, Shunbo Lei

TL;DR
This paper introduces BLADE, a federated online decision-making method that reduces communication costs while maintaining low regret in systems with stateful costs and partial client participation.
Contribution
The paper proposes BLADE, a novel blockwise federated online decision algorithm with provable regret bounds and low communication overhead, validated through experiments.
Findings
BLADE achieves O(T/K) communication complexity.
Sublinear regret is achieved when K=⟨√T⟩ and V_T=o(T^{1/4}).
Experiments validate communication-regret and other scaling effects.
Abstract
We study dynamic regret in federated online decision-making with stateful incurred costs under block-based synchronization and partial client participation. In this setting, sparse communication affects not only the pointwise update quality but also the realized state trajectory along which costs are incurred. We propose \textbf{BLADE}, a projected blockwise federated online decision method. BLADE uses only \(O(T/K)\) communication and achieves a dynamic-regret bound for the incurred cost against path-length-bounded comparator sequences; under \(K=\lceil\sqrt T\rceil\), the bound is sublinear whenever \(V_T=o(T^{1/4})\). Experiments on a controlled synthetic stable linear system validate the predicted communication--regret, memory, participation, disturbance-variation, and horizon-scaling effects.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
