2025
Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization
ICLR 2025poster
Gradient-based multi-objective optimization (MOO) is essential in modern machine learning, with applications in e.g., multi-task learning, federated learning, algorithmic fairness and reinforcement learning. In this work, we first reveal some limitations of Pareto stationarity, a widely accepted fi…