HATSolver: Learning Groebner Bases with Hierarchical Attention Transformers
Not on the map. Why?
Abstract (arXiv)
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)
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 38 references that are in the map. First posted on arXiv 9 Dec 2025.
Builds on
17 of 38 references.
References · 17
- 2017Attention Is All You Needcited by 59,932
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2019Neural Legal Judgment Prediction in Englishcited by 208
- 2023MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformerscited by 164
- 2019Neural Execution of Graph Algorithmscited by 118
- 2022An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classificationcited by 38
- 2021Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modelingcited by 35
- 2024Block Transformer: Global-to-Local Language Modeling for Fast Inferencecited by 32
- 2024SpaceByte: Towards Deleting Tokenization from Large Language Modelingcited by 31
- 2020Learning selection strategies in Buchberger's algorithmcited by 20
- 2023Neural Algorithmic Reasoning for Combinatorial Optimisationcited by 19
- 2025From Bytes to Ideas: Language Modeling with Autoregressive U-Netscited by 15
5 more
- 2025Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithmscited by 11
- 2025Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithmscited by 7
- 2022ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attentioncited by 6
- 2025Geometric Generality of Transformer-Based Gr"obner Basis Computationcited by 3
- 2024The Complexity of Algebraic Algorithms for LWEcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.