optimization challenges

5 papers

• FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization
• Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective
• Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
• WHAT MAKES MATH PROBLEMS HARD FOR REINFORCEMENT LEARNING: A CASE STUDY
• When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration