RECORD
Machine Learning Clifford invariants of ADE Coxeter elements
Machine Learning · Submitted 29 Sep 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim This paper is a pump-priming study in experimental mathematics using Clifford algebras, showing that such Clifford algebraic datasets are amenable to machine learning, and shedding light on relationships between these novel and other well-known geometric invariants and also giving rise to analytic results.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
There has been recent interest in novel Clifford geometric invariants of linear transformations. This motivates the investigation of such invariants for a certain type of geometric transformation of interest in the context of root systems, reflection groups, Lie groups and Lie algebras: the Coxeter transformations. We perform exhaustive calculations of all Coxeter transformations for $A_8$, $D_8$ and $E_8$ for a choice of basis of simple roots and compute their invariants, using high-performance computing. This computational algebra paradigm generates a dataset that can then be mined using techniques from data science such as supervised and unsupervised machine learning. In this paper we focus on neural network classification and principal component analysis. Since the output -- the invariants -- is fully determined by the choice of simple roots and the permutation order of the corresponding reflections in the Coxeter element, we expect huge degeneracy in the mapping. This provides the perfect setup for machine learning, and indeed we see that the datasets can be machine learned to very high accuracy. This paper is a pump-priming study in experimental mathematics using Clifford algebras, showing that such Clifford algebraic datasets are amenable to machine learning, and shedding light on relationships between these novel and other well-known geometric invariants and also giving rise to analytic results.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | There has been recent interest in novel Clifford geometric invariants of linear transformations. | background 1.00 | 0.04 | 0.02 | asserted 0.99 |
| s1 | This motivates the investigation of such invariants for a certain type of geometric transformation of interest in the context of root systems, reflection groups, Lie groups and Lie algebras: the Coxeter transformations. | background 0.93 | 0.09 | 0.03 | asserted 0.87 |
| s2 | We perform exhaustive calculations of all Coxeter transformations for $A_8$, $D_8$ and $E_8$ for a choice of basis of simple roots and compute their invariants, using high-performance computing. | method 0.72 | 0.97 | 0.04 | asserted 1.00 |
| s3 | This computational algebra paradigm generates a dataset that can then be mined using techniques from data science such as supervised and unsupervised machine learning. | method 0.79 | 0.58 | 0.06 | asserted 0.67 |
| s4 | In this paper we focus on neural network classification and principal component analysis. | method 0.83 | 0.65 | 0.04 | asserted 0.96 |
| s5 | Since the output -- the invariants -- is fully determined by the choice of simple roots and the permutation order of the corresponding reflections in the Coxeter element, we expect huge degeneracy in the mapping. | interpretation 0.92 | 0.28 | 0.05 | hedged possibility 0.69 |
| s6 | This provides the perfect setup for machine learning, and indeed we see that the datasets can be machine learned to very high accuracy. | result 0.95 | 0.93 | 0.35 | asserted 1.00 |
| s7 | This paper is a pump-priming study in experimental mathematics using Clifford algebras, showing that such Clifford algebraic datasets are amenable to machine learning, and shedding light on relationships between these novel and other well-known geometric invariants and also giving rise to analytic results. | contribution 0.64 | 0.85 | 0.74 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
There has been recent interest in novel Clifford geometric invariants of linear transformations. This motivates the investigation of such invariants for a certain type of geometric transformation of interest in the context of root systems, reflection groups, Lie groups and Lie algebras: the Coxeter transformations. We perform exhaustive calculations of all Coxeter transformations for $A_8$, $D_8$ and $E_8$ for a choice of basis of simple roots and compute their invariants, using high-performance computing. This computational algebra paradigm generates a dataset that can then be mined using techniques from data science such as supervised and unsupervised machine learning. In this paper we focus on neural network classification and principal component analysis. Since the output -- the invariants -- is fully determined by the choice of simple roots and the permutation order of the corresponding reflections in the Coxeter element, we expect huge degeneracy in the mapping. This provides the perfect setup for machine learning, and indeed we see that the datasets can be machine learned to very high accuracy. This paper is a pump-priming study in experimental mathematics using Clifford algebras, showing that such Clifford algebraic datasets are amenable to machine learning, and shedding light on relationships between these novel and other well-known geometric invariants and also giving rise to analytic results.
Human review
How the literature uses it
3 arXiv papers cite this in 3 sentences
Papers citing it
Cites it as background 3 papers
-
These are: supervised learning [ref] (introduced in [ref] ), unsupervised learning [ref] (introduced in [ref] ), and reinforcement learning [ref] (introduced in [ref] ); with notable introduction to string theory in [ref] .
Learning 3-Manifold Triangulations · Introduction · 0.93
-
As a final comment, we leave some reference to exciting applications of machine learning across alternative subfields in mathematical physics, which have included work on amoeba [ref] , branes [ref] , conformal theories [ref] , quivers [ref] , phenomenology [ref] , and other related geometry [ref] .
Calabi-Yau Four/Five/Six-folds as $\mathbb{P}^n_\textbf{w}$ Hypersurfaces: Machine Learning, Approximation, and Generation · Introduction · 0.99
-
For the interested reader, we include a few references on other applications of ML techniques to similar topics in string theory: [ref] .
Machine Learning Toric Duality in Brane Tilings · Introduction and summary · 0.99
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.