A Survey on the Use of Machine Learning within Computer Algebra
arXiv:2611.23361 · doi:10.1145/3831699
Abstract
This survey explores the use of Machine Learning (ML) in the field of Computer Algebra (CA), both to optimise existing CA algorithms, and to perform symbolic computation directly. Traditional symbolic methods, while mathematically rigorous, often are computationally expensive thus limiting their use in real-world applications. Recent advances have shown that data-driven techniques can address these limitations by guiding heuristic decisions, selecting optimal algorithms, predicting structural properties of algebraic objects, or even making direct symbolic computations. We take a systematic literature review approach and uncover work in CA applications including cylindrical algebraic decomposition, Gröbner basis computation, symbolic integration, and many more. The survey compares the different ML approaches that have been employed for these tasks, ranging from decision trees to transformers. Issues uncovered by the survey include the lack of benchmark datasets for CA, which hinders the comparison of methods and the generalizability of ML models. The survey identifies the potential for explainable AI tools to help develop trust in decisions, and to drive forward CA research itself.
arXiv comment31 pages
References in corpus (28)
- Measuring Mathematical Problem Solving With the MATH Dataset
- A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
- Dive into Deep Learning
- Determining the global minimum of Higgs potentials via Groebner bases - applied to the NMSSM
- Deciding the Consistency of Non-Linear Real Arithmetic Constraints with a Conflict Driven Search Using Cylindrical Algebraic Coverings
- Applying machine learning to the problem of choosing a heuristic to select the variable ordering for cylindrical algebraic decomposition
- Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models
- Improving multivariate Horner schemes with Monte Carlo tree search
- Problem formulation for truth-table invariant cylindrical algebraic decomposition by incremental triangular decomposition
- Using Machine Learning to Improve Cylindrical Algebraic Decomposition
- Explainable AI Insights for Symbolic Computation: A case study on selecting the variable ordering for cylindrical algebraic decomposition
- Comparing machine learning models to choose the variable ordering for cylindrical algebraic decomposition
- SYMBA: Symbolic Computation of Squared Amplitudes in High Energy Physics with Machine Learning
- Using Machine Learning to Decide When to Precondition Cylindrical Algebraic Decomposition With Groebner Bases
- Machine Learning for Mathematical Software
- The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)
- ODEbase: A Repository of ODE Systems for Systems Biology
- Levelwise construction of a single cylindrical algebraic cell
- Symbolic Equation Solving via Reinforcement Learning
- New heuristic to choose a cylindrical algebraic decomposition variable ordering motivated by complexity analysis
- Improved cross-validation for classifiers that make algorithmic choices to minimise runtime without compromising output correctness
- Generating Elementary Integrable Expressions
- A machine learning based software pipeline to pick the variable ordering for algorithms with polynomial inputs
- Lessons on Datasets and Paradigms in Machine Learning for Symbolic Computation: A Case Study on CAD
- The Liouville Generator for Producing Integrable Expressions
- Learning a performance metric of Buchberger's algorithm
- Symbolic integration by integrating learning models with different strengths and weaknesses
- What is my math transformer doing? -- Three results on interpretability and generalization