Post-Cutoff.com
  1. Home
  2. Timeline
  3. 2021
  4. DeepMind and mathematicians use machine learning to guide…

DeepMind and mathematicians use machine learning to guide new theorems in knot theory and representation theory

★★★scienceDeepMindUniversity of OxfordUniversity of Sydneyconfidence: high

Davies et al. (Nature, Dec 2021) used supervised learning plus attribution to point mathematicians to hidden relationships. That led to a new theorem linking the knot signature to hyperbolic geometry, and to progress on the combinatorial invariance conjecture for Kazhdan–Lusztig polynomials.

Key facts

Science result

Field
mathematics / knot theory / representation theory
Problem
Combinatorial invariance conjecture for Kazhdan–Lusztig polynomials; relations between knot invariants
Result
ML-guided discovery of a conjectured, then proved, relation between the knot signature and hyperbolic invariants, and a new approach to combinatorial invariance for symmetric groups.
AI system
supervised neural networks with gradient saliency
Human role
Human-led with AI tools: ML suggested patterns; mathematicians formulated and proved the theorems
Verification
Peer-reviewed in Nature; human proofs
Status
confirmed

What happened

DeepMind trained models to predict one mathematical quantity from others, then used attribution to show which inputs mattered, prompting expert mathematicians to formulate and prove new results.

Why it matters

It was the first Nature-level demonstration of AI contributing to pure maths research, as an intuition aid rather than a prover.

Changelog

  • 2026-09-29: created

Related events

  1. FunSearch: an LLM finds new cap-set constructions, the first LLM discovery in open maths ★★★★

Sources (2)

id: 2021-12-01-deepmind-knot-theory-intuition · updated 2026-09-29 · open in the interactive timeline