No AI summary available for this article.
Why It Matters
Communication-efficient federated optimization commonly spends several gradient evaluations between server updates.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Communication-efficient federated optimization commonly spends several gradient evaluations between server updates. Existing local-update methods use this computation to advance an independent model on each client. Under heterogeneous data, however, these models evaluate gradients at different locations, making the aggregated update difficult to interpret as a gradient of the global objective. We study an alternative use of the same computation budget: \emph{evaluate the global objective along a shared, predicted path}. We propose Common-Trajectory Predictive Federated Learning (\texttt{CTP-FL...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.35130v1 · Indexed about 1 hour ago