AINeutralarXiv – CS AI · 7h ago6/10
🧠
A Unified Framework for Gradient Aggregation in Multi-Objective Optimization
Researchers present a unified mathematical framework for gradient aggregation in multi-objective optimization (MOO), establishing convergence guarantees to Pareto stationarity. The work reveals that non-conflicting gradient directions within the convex hull satisfy sufficient conditions for convergence, enabling broader algorithmic approaches including a new method called capped MGDA for federated learning applications.