Learning to unknot

@article{Gukov2021LearningTU,
  title={Learning to unknot},
  author={Sergei Gukov and James Halverson and Fabian Ruehle and Piotr Sulkowski},
  journal={Machine Learning: Science and Technology},
  year={2021},
  volume={2}
}
We introduce natural language processing into the study of knot theory, as made natural by the braid word representation of knots. We study the UNKNOT problem of determining whether or not a given knot is the unknot. After describing an algorithm to randomly generate N-crossing braids and their knot closures and discussing the induced prior on the distribution of knots, we apply binary classification to the UNKNOT decision problem. We find that the Reformer and shared-QK Transformer network… Expand
Heterotic String Model Building with Monad Bundles and Reinforcement Learning
TLDR
By focusing on two specific manifolds with Picard numbers two and three, it is shown that reinforcement learning can be used successfully to explore monad bundles and hundreds of new candidate standard models are found. Expand
Performance of the Uniform Closure Method for open knotting as a Bayes-type classifier
The discovery of knotting in proteins and other macromolecular chains has motivated researchers to more carefully consider how to identify and classify knots in open arcs. Most definitions classifyExpand
Particle Physics Model Building with Reinforcement Learning
In this paper, we apply reinforcement learning to particle physics model building. As an example environment, we use the space of Froggatt-Nielsen type models for quark masses. Using a basicExpand
Quark Mass Models and Reinforcement Learning
Abstract In this paper, we apply reinforcement learning to the problem of constructing models in particle physics. As an example environment, we use the space of Froggatt-Nielsen type models forExpand
Untangling Braids with Multi-agent Q-Learning
TLDR
The results provide evidence that the more the system is trained, the better the untangling player gets at untangling braids, and at the same time, the tangling player produces good examples of tangled braids. Expand
Neural Network Approximations for Calabi-Yau Metrics
Vishnu Jejjalaa , Damián Kaloni Mayorga Peñaa,b , Challenger Mishrac Mandelstam Institute for Theoretical Physics, School of Physics, NITheP, and CoE-MaSS, University of the Witwatersrand,Expand
Universes as big data
  • Yanghui He
  • Physics, Mathematics
  • International Journal of Modern Physics A
  • 2021
In this paper, we briefly overview how, historically, string theory led theoretical physics first to precise problems in algebraic and differential geometry, and thence to computational geometry inExpand
Topological Link Models of Multipartite Entanglement
We introduce a novel model of multipartite entanglement based on topological links, generalizing the graph/hypergraph entropy cone program. We demonstrate that there exist link representations ofExpand
Machine-Learning Mathematical Structures
TLDR
Focusing on supervised machine-learning on labeled data from different fields ranging from geometry to representation theory, from combinatorics to number theory, a comparative study of the accuracies on different problems is presented. Expand
Disentangling a Deep Learned Volume Formula
TLDR
A simple phenomenological formula is presented which approximates the hyperbolic volume of a knot using only a single evaluation of its Jones polynomial at a root of unity using an analytically continued Chern-Simons integration cycle. Expand
...
1
2
...

References

SHOWING 1-10 OF 69 REFERENCES
Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning
TLDR
It is found that word embeddings capture a surprising amount of information, and that, under suitable supervised training, vector subtraction generalises well to a broad range of relations, including over unseen lexical items. Expand
Machine-learning the string landscape
Abstract We propose a paradigm to apply machine learning various databases which have emerged in the study of the string landscape. In particular, we establish neural networks as both classifiers andExpand
KnotProt: a database of proteins with knots and slipknots
TLDR
The protein topology database KnotProt, http://knotprot.cent.uw.edu.pl/, collects information about protein structures with open polypeptide chains forming knots or slipknots and presents extensive information about the biological functions, families and fold types of proteins with non-trivial knotting. Expand
The Unbearable Hardness of Unknotting
We prove that deciding if a diagram of the unknot can be untangled using at most $k$ Riedemeister moves (where $k$ is part of the input) is NP-hard. We also prove that several natural questionsExpand
Deep learning the hyperbolic volume of a knot
Abstract An important conjecture in knot theory relates the large-N, double scaling limit of the colored Jones polynomial J K , N ( q ) of a knot K to the hyperbolic volume of the knot complement,Expand
Neural Machine Translation by Jointly Learning to Align and Translate
TLDR
It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. Expand
Mastering the game of Go with deep neural networks and tree search
TLDR
Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go. Expand
Reformer: The Efficient Transformer
TLDR
This work replaces dot-product attention by one that uses locality-sensitive hashing and uses reversible residual layers instead of the standard residuals, which allows storing activations only once in the training process instead of several times, making the model much more memory-efficient and much faster on long sequences. Expand
Deep-Learning the Landscape
  • Y. He
  • Physics, Mathematics
  • 2017
We propose a paradigm to deep-learn the ever-expanding databases which have emerged in mathematical physics and particle phenomenology, as diverse as the statistics of string vacua or combinatorialExpand
Verification Of The Jones Unknot Conjecture Up To 22 Crossings
We proved by computer enumeration that the Jones polynomial distinguishes the unknot for knots up to 22 crossings. Following an approach of Yamada, we generated knot diagrams by inserting algebraicExpand
...
1
2
3
4
5
...