[2603.27962] Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees

Computer Science > Machine Learning arXiv:2603.27962 (cs) [Submitted on 30 Mar 2026] Title:Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees Authors:Ziqin Chen, Yongqiang Wang View a PDF of the paper titled Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees, by Ziqin Chen and Yongqiang Wang View PDF HTML (experimental) Abstract:Distributed learning has gained significant attention due to its advantages in scalability, privacy, and fault this http URL this paradigm, multiple agents collaboratively train a global model by exchanging parameters only with their neighbors. However, a key vulnerability of existing distributed learning approaches is their implicit assumption that all agents behave honestly during gradient updates. In real-world scenarios, this assumption often breaks down, as selfish or strategic agents may be incentivized to manipulate gradients for personal gain, ultimately compromising the final learning outcome. In this work, we propose a fully distributed payment mechanism that, for the first time, guarantees both truthful behaviors and accurate convergence in distributed stochastic gradient descent. This represents a significant advancement, as it overcomes two major limitations of existing truthfulness mechanisms for collaborative learning:(1) reliance on a centralized server for payment ...