mlsanityData to 14 Oct 2026

Is deep learning a useful tool for the pure mathematician?

arXiv 2304.12602 ↗First posted 25 Apr 2023math.RT cs.LG math.AGcited by 14

Not on the map. Why?

Abstract (arXiv)

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

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

12 of 49 references.

References · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  3. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 927
  4. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 291
  5. 2021Proof Artifact Co-training for Theorem Proving with Language Modelscited by 132
  6. 2021Linear algebra with transformerscited by 63
  7. 2021Constructions in combinatorics via neural networkscited by 48
  8. 2020Learning selection strategies in Buchberger's algorithmcited by 20
  9. 2019Learning Algebraic Structures: Preliminary Investigationscited by 15
  10. 2021The signature and cusp geometry of hyperbolic knotscited by 8
  11. 2020Deep Learning Gauss-Manin Connectionscited by 4
  12. 2021Learning proofs for the classification of nilpotent semigroupscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 1; 2025: 4; 2026: 3.

14 papers.

Sort: