# Is deep learning a useful tool for the pure mathematician?

arXiv: https://arxiv.org/abs/2304.12602 · HTML: https://mlsanity.com/paper/2304.12602/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 49 references that are in the map.
- First posted on arXiv 25 Apr 2023.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs](https://mlsanity.com/paper/2210.12283/) (2022)
- [Proof Artifact Co-training for Theorem Proving with Language Models](https://mlsanity.com/paper/2102.06203/) (2021)
- [Linear algebra with transformers](https://mlsanity.com/paper/2112.01898/) (2021)
- [Constructions in combinatorics via neural networks](https://mlsanity.com/paper/2104.14516/) (2021)
- [Learning selection strategies in Buchberger's algorithm](https://mlsanity.com/paper/2005.01917/) (2020)
- [Learning Algebraic Structures: Preliminary Investigations](https://mlsanity.com/paper/1905.02263/) (2019)
- [The signature and cusp geometry of hyperbolic knots](https://mlsanity.com/paper/2111.15323/) (2021)
- [Deep Learning Gauss-Manin Connections](https://mlsanity.com/paper/2007.13786/) (2020)
- [Learning proofs for the classification of nilpotent semigroups](https://mlsanity.com/paper/2106.03015/) (2021)

## Built on by (most cited first, 14 of 14)

- [How does over-squashing affect the power of GNNs?](https://mlsanity.com/paper/2306.03589/) (2023)
- [Asynchronous Algorithmic Alignment with Cocycles](https://mlsanity.com/paper/2306.15632/) (2023)
- [Machine learning detects terminal singularities](https://mlsanity.com/paper/2310.20458/) (2023)
- [Large Language Models for Mathematicians](https://mlsanity.com/paper/2312.04556/) (2023)
- [A Triumvirate of AI Driven Theoretical Discovery](https://mlsanity.com/paper/2405.19973/) (2024)
- [Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?](https://mlsanity.com/paper/2501.18527/) (2025)
- [Machine learning assisted exploration for affine Deligne-Lusztig varieties](https://mlsanity.com/paper/2308.11355/) (2023)
- [Adaptive Monte Carlo Search for Conjecture Refutation in Graph Theory](https://mlsanity.com/paper/2306.07956/) (2023)
- [Explaining Deep Network Classification of Matrices: A Case Study on Monotonicity](https://mlsanity.com/paper/2507.22570/) (2025)
- [Mapping Uncharted Symmetries: Machine Discovery in Combinatorics](https://mlsanity.com/paper/2605.19063/) (2026)
- [Colored Jones Polynomials and the Volume Conjecture](https://mlsanity.com/paper/2502.18575/) (2025)
- [A Hybrid Framework for Healing Semigroups with Machine Learning](https://mlsanity.com/paper/2509.01763/) (2025)
- [Murmurations: a case study in AI-assisted mathematics](https://mlsanity.com/paper/2603.09680/) (2026)
- [Totally Positive Matrices and the Highest-Order Coefficients of the Characteristic Polynomial](https://mlsanity.com/paper/2607.18148/) (2026)

## Abstract (arXiv)

A personal and informal account of what a pure mathematician might expect when using tools from deep learning in their research.