Tag
The paper introduces FedeRage, a risk-averse federated learning method that uses conditional value-at-risk to address unknown client participation and heterogeneity, demonstrating enhanced accuracy, fairness, and convergence in experiments.
This paper presents an online, distribution-free framework for controlling Conditional Value-at-Risk (CVaR) in adversarial and non-stationary environments, with asymptotic guarantees and applications in portfolio risk management and LLM toxicity mitigation.