Not Every Term Adds New Structure: Sobolev Novelty for Symbolic Regression
Sobolev Novelty is introduced, a term-level measure of structural independence for symbolic equations, which can be incorporated into diverse SR paradigms to support term pruning, search guidance, LLM feedback, and data selection, yielding consistent performance gains and demonstrating broad applicability.
Boxiao Wang, Kai Li, Yu-Heng Jing et al.
· 0 citations