Saved in:
Bibliographic Details
Main Authors: Malhou, Mohamed, Perret, Ludovic, Lauter, Kristin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.14722
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909966089060352
author Malhou, Mohamed
Perret, Ludovic
Lauter, Kristin
author_facet Malhou, Mohamed
Perret, Ludovic
Lauter, Kristin
contents At NeurIPS 2024, Kera et al. introduced the use of transformers for computing Groebner bases, a central object in computer algebra with numerous practical applications. In this paper, we improve this approach by applying Hierarchical Attention Transformers (HATs) to solve systems of multivariate polynomial equations via Groebner bases computation. The HAT architecture incorporates a tree-structured inductive bias that enables the modeling of hierarchical relationships present in the data and thus achieves significant computational savings compared to conventional flat attention models. We generalize to arbitrary depths and include a detailed computational cost analysis. Combined with curriculum learning, our method solves instances that are much larger than those in Kera et al. (2024 Learning to compute Groebner bases)
format Preprint
id arxiv_https___arxiv_org_abs_2512_14722
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HATSolver: Learning Groebner Bases with Hierarchical Attention Transformers
Malhou, Mohamed
Perret, Ludovic
Lauter, Kristin
Machine Learning
Artificial Intelligence
At NeurIPS 2024, Kera et al. introduced the use of transformers for computing Groebner bases, a central object in computer algebra with numerous practical applications. In this paper, we improve this approach by applying Hierarchical Attention Transformers (HATs) to solve systems of multivariate polynomial equations via Groebner bases computation. The HAT architecture incorporates a tree-structured inductive bias that enables the modeling of hierarchical relationships present in the data and thus achieves significant computational savings compared to conventional flat attention models. We generalize to arbitrary depths and include a detailed computational cost analysis. Combined with curriculum learning, our method solves instances that are much larger than those in Kera et al. (2024 Learning to compute Groebner bases)
title HATSolver: Learning Groebner Bases with Hierarchical Attention Transformers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.14722