3 papers
cs.LG2026
Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning
Jingfeng Zhong, Zhengxiang Liu, Zhijie Wang +1
The discovery of first integrals is of fundamental scientific importance for understanding conservation laws in dynamical systems. However, existing symbolic computation tools and…
cs.LG2026
From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models
Jianan Yang, Yiran Wang, Shuai Li +3
Physics-informed neural networks (PINNs) offer a mesh-free framework for solving partial differential equations (PDEs), yet training often suffers from gradient pathologies, spectr…
cs.LG2025
Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond
Canzhe Zhao, Shinji Ito, Shuai Li
Heavy-tailed bandits have been extensively studied since the seminal work of \citet{Bubeck2012BanditsWH}. In particular, heavy-tailed linear bandits, enabling efficient learning wi…