Function Trees: Transparent Machine Learning

arXiv:2403.13141v1 Announce Type: cross
Abstract: The output of a machine learning algorithm can usually be represented by one or more multivariate functions of its input variables. Knowing the global properties of such functions can help in understanding the system that produced the data as well as interpreting and explaining corresponding model predictions. A method is presented for representing a general multivariate function as a tree of simpler functions. This tree exposes the global internal structure of the function by uncovering …

abstract algorithm arxiv cs.lg data function functions global machine machine learning multivariate predictions stat.ml transparent trees type understanding variables