mlsanityData to 7 Oct 2026

If you can distinguish, you can express: Galois theory, Stone--Weierstrass, machine learning, and linguistics

arXiv 2510.09902 ↗First posted 10 Oct 2025math.HO stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

This essay develops a parallel between the Fundamental Theorem of Galois Theory and the Stone--Weierstrass theorem: both can be viewed as assertions that tie the distinguishing power of a class of objects to their expressive power. We provide an elementary theorem connecting the relevant notions of "distinguishing power". We also discuss machine learning and data science contexts in which these theorems, and more generally the theme of links between distinguishing power and expressive power, appear. Finally, we discuss the same theme in the context of linguistics, where it appears as a foundational principle, and illustrate it with several examples.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 91 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

24 of 91 references.

References · 24

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  2. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  3. 2019Benign Overfitting in Linear Regressioncited by 544
  4. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 182
  5. 2019On the equivalence between graph isomorphism testing and function approximation with GNNscited by 172
  6. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 166
  7. 2019On the Universality of Invariant Networkscited by 151
  8. 2018Universal approximations of invariant maps by neural networkscited by 127
  9. 2021Weisfeiler and Leman go Machine Learning: The Story so farcited by 121
  10. 2022Equivariance with Learned Canonicalization Functionscited by 106
  11. 2020On the Universality of Rotation Equivariant Point Cloud Networkscited by 80
  12. 2020Universal Equivariant Multilayer Perceptronscited by 49
12 more
  1. 2022Low Dimensional Invariant Embeddings for Universal Geometric Learningcited by 38
  2. 2023Fine-grained Expressivity of Graph Neural Networkscited by 25
  3. 2022Group-invariant max filteringcited by 18
  4. 2017Estimation under group actions: recovering orbits from invariantscited by 14
  5. 2023Towards fully covariant machine learningcited by 10
  6. 2021Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EMcited by 5
  7. 2021The generalized method of moments for multi-reference alignmentcited by 4
  8. 2022Max filtering with reflection groupscited by 4
  9. 2025On Universality Classes of Equivariant Networkscited by 4
  10. 2021Dihedral multi-reference alignmentcited by 3
  11. 2021Sparse multi-reference alignment: sample complexity and computational hardnesscited by 2
  12. 2025The generalized phase retrieval problem over compact groupscited by 1

Built on by

Not cited yet.