ID: 1906.08730

Machine Learning Line Bundle Cohomology

June 20, 2019

View on ArXiv
Callum R. Brodie, Andrei Constantin, Rehan Deen, Andre Lukas
High Energy Physics - Theory

We investigate different approaches to machine learning of line bundle cohomology on complex surfaces as well as on Calabi-Yau three-folds. Standard function learning based on simple fully connected networks with logistic sigmoids is reviewed and its main features and shortcomings are discussed. It has been observed recently that line bundle cohomology can be described by dividing the Picard lattice into certain regions in each of which the cohomology dimension is described by a polynomial formula. Based on this structure, we set up a network capable of identifying the regions and their associated polynomials, thereby effectively generating a conjecture for the correct cohomology formula. For complex surfaces, we also set up a network which learns certain rigid divisors which appear in a recently discovered master formula for cohomology dimensions.

Similar papers 1

Machine Learning Line Bundle Cohomologies of Hypersurfaces in Toric Varieties

September 7, 2018

90% Match
Daniel Klaewer, Lorenz Schlechter
High Energy Physics - Theory

Different techniques from machine learning are applied to the problem of computing line bundle cohomologies of (hypersurfaces in) toric varieties. While a naive approach of training a neural network to reproduce the cohomologies fails in the general case, by inspecting the underlying functional form of the data we propose a second approach. The cohomologies depend in a piecewise polynomial way on the line bundle charges. We use unsupervised learning to separate the different ...

Find SimilarView on arXiv

Formulae for Line Bundle Cohomology on Calabi-Yau Threefolds

August 29, 2018

88% Match
Andrei Constantin, Andre Lukas
Algebraic Geometry

We present closed form expressions for the ranks of all cohomology groups of holomorphic line bundles on several Calabi-Yau threefolds realised as complete intersections in products of projective spaces. The formulae have been obtained by systematising and extrapolating concrete calculations and they have been checked computationally. Although the intermediate calculations often involve laborious computations of ranks of Leray maps in the Koszul spectral sequence, the final r...

Find SimilarView on arXiv
Anthony Ashmore, Rehan Deen, ... , Ovrut Burt A.
High Energy Physics - Theory

We study the use of machine learning for finding numerical hermitian Yang-Mills connections on line bundles over Calabi-Yau manifolds. Defining an appropriate loss function and focusing on the examples of an elliptic curve, a K3 surface and a quintic threefold, we show that neural networks can be trained to give a close approximation to hermitian Yang-Mills connections.

Machine Learning Calabi-Yau Four-folds

September 5, 2020

87% Match
Yang-Hui He, Andre Lukas
Algebraic Geometry
Machine Learning

Hodge numbers of Calabi-Yau manifolds depend non-trivially on the underlying manifold data and they present an interesting challenge for machine learning. In this letter we consider the data set of complete intersection Calabi-Yau four-folds, a set of about 900,000 topological types, and study supervised learning of the Hodge numbers h^1,1 and h^3,1 for these manifolds. We find that h^1,1 can be successfully learned (to 96% precision) by fully connected classifier and regress...

Find SimilarView on arXiv

Deep multi-task mining Calabi-Yau four-folds

August 4, 2021

86% Match
Harold Erbin, Riccardo Finotello, ... , Tamaazousti Mohamed
Machine Learning
Algebraic Geometry

We continue earlier efforts in computing the dimensions of tangent space cohomologies of Calabi-Yau manifolds using deep learning. In this paper, we consider the dataset of all Calabi-Yau four-folds constructed as complete intersections in products of projective spaces. Employing neural networks inspired by state-of-the-art computer vision architectures, we improve earlier benchmarks and demonstrate that all four non-trivial Hodge numbers can be learned at the same time using...

Find SimilarView on arXiv

Constructing and Machine Learning Calabi-Yau Five-folds

October 24, 2023

86% Match
R. Alawadhi, D. Angella, ... , Gherardini T. Schettini
Machine Learning
Algebraic Geometry

We construct all possible complete intersection Calabi-Yau five-folds in a product of four or less complex projective spaces, with up to four constraints. We obtain $27068$ spaces, which are not related by permutations of rows and columns of the configuration matrix, and determine the Euler number for all of them. Excluding the $3909$ product manifolds among those, we calculate the cohomological data for $12433$ cases, i.e. $53.7 \%$ of the non-product spaces, obtaining $2375...

Find SimilarView on arXiv

Holomorphic feedforward networks

May 9, 2021

85% Match
Michael R. Douglas
Complex Variables
Numerical Analysis
Numerical Analysis

A very popular model in machine learning is the feedforward neural network (FFN). The FFN can approximate general functions and mitigate the curse of dimensionality. Here we introduce FFNs which represent sections of holomorphic line bundles on complex manifolds, and ask some questions about their approximating power. We also explain formal similarities between the standard approach to supervised learning and the problem of finding numerical Ricci flat K\"ahler metrics, which...

Find SimilarView on arXiv

Deep learning complete intersection Calabi-Yau manifolds

November 20, 2023

85% Match
Harold Erbin, Riccardo Finotello
Machine Learning
Algebraic Geometry

We review advancements in deep learning techniques for complete intersection Calabi-Yau (CICY) 3- and 4-folds, with the aim of understanding better how to handle algebraic topological data with machine learning. We first discuss methodological aspects and data analysis, before describing neural networks architectures. Then, we describe the state-of-the art accuracy in predicting Hodge numbers. We include new results on extrapolating predictions from low to high Hodge numbers,...

Find SimilarView on arXiv

Machine learning for complete intersection Calabi-Yau manifolds: a methodological study

July 30, 2020

84% Match
Harold Erbin, Riccardo Finotello
Machine Learning
Algebraic Geometry

We revisit the question of predicting both Hodge numbers $h^{1,1}$ and $h^{2,1}$ of complete intersection Calabi-Yau (CICY) 3-folds using machine learning (ML), considering both the old and new datasets built respectively by Candelas-Dale-Lutken-Schimmrigk / Green-H\"ubsch-Lutken and by Anderson-Gao-Gray-Lee. In real world applications, implementing a ML system rarely reduces to feed the brute data to the algorithm. Instead, the typical workflow starts with an exploratory dat...

Find SimilarView on arXiv

Machine Learned Calabi-Yau Metrics and Curvature

November 17, 2022

84% Match
Per Berglund, Giorgi Butbaia, Tristan Hübsch, Vishnu Jejjala, Damián Mayorga Peña, ... , Tan Justin
Machine Learning
Algebraic Geometry
Differential Geometry

Finding Ricci-flat (Calabi-Yau) metrics is a long standing problem in geometry with deep implications for string theory and phenomenology. A new attack on this problem uses neural networks to engineer approximations to the Calabi-Yau metric within a given K\"ahler class. In this paper we investigate numerical Ricci-flat metrics over smooth and singular K3 surfaces and Calabi-Yau threefolds. Using these Ricci-flat metric approximations for the Cefal\'u family of quartic twofol...

Find SimilarView on arXiv