Teaching the Teacher: The Role of Teacher-Student Smoothness Alignment in Genetic Programming-based Symbolic Distillation

arXiv:2507.22767v3 Announce Type: replace-cross Abstract: Obtaining human-readable symbolic formulas via genetic programming-based symbolic distillation of a deep neural network trained on a target dataset presents a promising yet underexplored pathway toward explainable artificial intelligence (XAI). However, the standard pipeline frequently yields symbolic models with poor predictive accuracy. We identify a fundamental misalignment in functional complexity as the primary barrier to achieving b