Decentralized Federated Learning lets every client reach the global minimum with zero performance gap and at the same convergence rate as centralized methods, but only when the loss function is smooth and strongly convex.
Source quote, verbatim
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.
From
Wulf A. Kaal, AI Governance Via Web3 Reputation System (2024), Adapting Decentralization of AI Governance to AI Models, p. 25 https://ssrn.com/abstract=4941807 · source PDF
Cite as
Wulf A. Kaal, AI Governance Via Web3 Reputation System (2024). SSRN: https://ssrn.com/abstract=4941807
Holds when
when the loss function is smooth and strongly convex
restateskaal:claim:4796714-031 Decentralized Federated Learning reaches the global minimum with zero performance gap and matches the converge...
Verify
The quote above is an exact substring of the source PDF, whose sha256 is ab66c1e99a88da1fa36b0c6b536df5184231fe6aa427f3dd53287a4e0ac79853. Extraction method: pdf-text-layer. Attestation record: colloquium/attestations/281fac19e63af7ce...json Verify the binding yourself: curl -s https://wulfkaal.github.io/claims/4941807-026.md | sha256sum