# kaal:claim:4941807-026

**Claim.** 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.

**Type.** condition  **Support.** evidenced

**Holds when.**

- when the loss function is smooth and strongly convex

**Source quote.**

> 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, page 25

**Cite as.** Wulf A. Kaal, AI Governance Via Web3 Reputation System (2024). SSRN: https://ssrn.com/abstract=4941807

**Verify.** sha256 of source PDF `ab66c1e99a88da1fa36b0c6b536df5184231fe6aa427f3dd53287a4e0ac79853` at https://raw.githubusercontent.com/wulfkaal/Academic-Papers/main/papers/pdf/Kaal%20-%202024%20-%20AI%20Governance%20Via%20Web3%20Reputation%20System.pdf

**Topics.** decentralization, ai-and-agents

**Keywords.** decefl, federated-learning, convergence, decentralized-ai, performance

**Related claims.**

- restates: https://wulfkaal.github.io/claims/4796714-031

**Canonical form.** This markdown file is the canonical hashed representation of the claim. Its sha256 is the content hash used for attestation.