Learning knot invariants across dimensions

Abstract

We use deep neural networks to machine learn correlations between knot invariants in various dimensions. The three-dimensional invariant of interest is the Jones polynomial $J(q)$, and the four-dimensional invariants are the Khovanov polynomial $\text{Kh}(q,t)$, smooth slice genus $g$, and Rasmussen's $s$-invariant. We find that a two-layer feed-forward neural network can predict $s$ from $\text{Kh}(q,-q^{-4})$ with greater than $99\%$ accuracy. A theoretical explanation for this performance exists in knot theory via the now disproven knight move conjecture, which is obeyed by all knots in our dataset. More surprisingly, we find similar performance for the prediction of $s$ from $\text{Kh}(q,-q^{-2})$, which suggests a novel relationship between the Khovanov and Lee homology theories of a knot. The network predicts $g$ from $\text{Kh}(q,t)$ with similarly high accuracy, and we discuss the extent to which the machine is learning $s$ as opposed to $g$, since there is a general inequality $|s|\le 2g$. The Jones polynomial, as a three-dimensional invariant, is not obviously related to $s$ or $g$, but the network achieves greater than $95\%$ accuracy in predicting either from $J(q)$. Moreover, similar accuracy can be achieved by evaluating $J(q)$ at roots of unity. This suggests a relationship with $SU(2)$ Chern--Simons theory, and we review the gauge theory construction of Khovanov homology which may be relevant for explaining the network's performance.

arXiv commentv1: 35 pages, 6 figures; v2: 36 pages, 6 figures, figures updated, typos corrected

References in corpus (23)

• Liouville Correlation Functions from Four-dimensional Gauge Theories
• Analytic Continuation Of Chern-Simons Theory
• Three-Dimensional Quantum Gravity, Chern-Simons Theory, and the A-Polynomial
• On Khovanov's categorification of the Jones polynomial
• M5-Branes, D4-Branes and Quantum 5D super-Yang-Mills
• On D=5 super Yang-Mills theory and (2,0) theory
• Knot Invariants from Four-Dimensional Gauge Theory
• On the Khovanov and knot Floer homologies of quasi-alternating links
• Man and machine thinking about the smooth 4-dimensional Poincaré conjecture
• Knots-quivers correspondence
• The support of the Khovanov's invariants for alternating knots
• Gauge theory and Rasmussen's invariant
• Deep Learning the Hyperbolic Volume of a Knot
• Alternating links and definite surfaces
• A characterisation of alternating knot exteriors
• Sequencing BPS Spectra
• Index Formulae for Line Bundle Cohomology on Complex Surfaces
• Disentangling a Deep Learned Volume Formula
• The Distribution of Knots in the Petaluma Model
• Mapper-type algorithms for complex data and relations
• Filtrations on instanton homology
• Big Data Approaches to Knot Theory: Understanding the Structure of the Jones Polynomial
• The Lee Spectral Sequence, Unknotting Number, and the Knight Move Conjecture

Cited by in corpus (3)

• Unsupervised Learning of Topological Non-Abelian Braiding in Non-Hermitian Bands
• Black holes and the loss landscape in machine learning
• Learning 3-Manifold Triangulations