5 papers
Beyond Accuracy and Complexity: The Effective Information Criterion for Structurally Stable Symbolic Regression
Zihan Yu, Guanren Wang, Jingtao Ding +2
Symbolic regression (SR) traditionally balances accuracy and complexity, implicitly assuming that simpler formulas are structurally more rational. We argue that this assumption is…
Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length
Zihan Yu, Jingtao Ding, Yong Li +1
Symbolic regression, a task discovering the formula best fitting the given data, is typically based on the heuristical search. These methods usually update candidate formulas to ob…
A Comprehensive Survey on Artificial Intelligence for Complex Network: Potential, Methodology and Application
Jingtao Ding, Chang Liu, Yu Zheng +8
Complex networks pervade various real-world systems, from the natural environment to human societies. The essence of these networks is in their ability to transition and evolve fro…
Beyond Equilibrium: Non-Equilibrium Foundations Should Underpin Generative Processes in Complex Dynamical Systems
Jiazhen Liu, Ruikun Li, Huandong Wang +4
This position paper argues that next-generation non-equilibrium-inspired generative models will provide the essential foundation for better modeling real-world complex dynamical sy…
Human Behavior Simulation: Objectives, Methodologies, and Open Problems
Zhang Guozhen, Yu Zihan, Li Nian +4
In recent years, human behavior simulation has drawn increasing attention from both academia and industry. The reasons fall into two aspects. First, simulation serves as a critical…