Can We Count on Deep Learning: Exploring and Characterizing Combinatorial Structures Using Machine Learning

Helen Jenne, Herman Chau, Davis Brown, Jackson Warley, Timothy Doster, Henry Kvinge

Keywords: Deep learning for pure math, deep learning explainability, combinatorics, symmetric group, Shapley values

TL;DR: We propose a method of using deep learning to find human interpretable characterizations of sets of mathematical objects

Abstract: With its exceptional pattern matching ability, deep learning has proven to be a powerful tool in a range of scientific domains. This is increasingly true in research mathematics, where recent work has demonstrated deep learning's ability to highlight subtle connections between mathematical objects that might escape a human expert. In this work we describe a simple method to help domain experts characterize a set of mathematical objects using deep learning. Such *characterization problems* often occur when some particular class of function, space, linear representation, etc. naturally emerges in calculations or other means but lacks a simple description. The goal is to find simple rules that also ideally shed light on the underlying mathematics. Our method, which we call *Feature Attribution Clustering for Exploration (FACE)*, clusters the feature attribution representations extracted from a trained model, arriving at a short list of prototype attributions that the domain expert can then try to convert into formal and rigorous rules. As a case study, we use our method to derive a new result in combinatorics by characterizing a subset of 0-1 matrices that corresponds to certain representations of permutations known as two-sided ordered words.

Submission Number: 10