kaal:claim:4796714-031

Decentralized Federated Learning reaches the global minimum with zero performance gap and matches the convergence rate of centralized methods when the loss function is smooth and strongly convex.

The DeceFL approach ensures that every client can reach the global minimum with zero performance gap and achieve the same convergence rate as centralized methods when the loss function is smooth and strongly convex.

Wulf A. Kaal, AI Governance (2024), Adapting Decentralization of AI Governance to AI Models, p. 34
https://ssrn.com/abstract=4796714 · source PDF

Wulf A. Kaal, AI Governance (2024). SSRN: https://ssrn.com/abstract=4796714

• requires a smooth and strongly convex loss function
• demonstrated across convex and nonconvex losses, time invariant and time varying topologies, and IID and non-IID datasets

empiricalsupport: evidenceddecentralization

• restated_by kaal:claim:4941807-026 Decentralized Federated Learning lets every client reach the global minimum with zero performance gap and at t...

The quote above is an exact substring of the source PDF, whose sha256 is 59fa63bae179e8f9b6b8efbdf90cee28400276512a1b04f9f579a48641305c93. Extraction method: pdf-text-layer.
Attestation record: colloquium/attestations/8a135b76e1d31960...json
Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/4796714-031.md | sha256sum