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

Abstract

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-Hübsch-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 data analysis (EDA) which aims at understanding better the input data and finding an optimal representation. It is followed by the design of a validation procedure and a baseline model. Finally, several ML models are compared and combined, often involving neural networks with a topology more complicated than the sequential models typically used in physics. By following this procedure, we improve the accuracy of ML computations for Hodge numbers with respect to the existing literature. First, we obtain 97% (resp. 99%) accuracy for $h^{1,1}$ using a neural network inspired by the Inception model for the old dataset, using only 30% (resp. 70%) of the data for training. For the new one, a simple linear regression leads to almost 100% accuracy with 30% of the data for training. The computation of $h^{2,1}$ is less successful as we manage to reach only 50% accuracy for both datasets, but this is still better than the 16% obtained with a simple neural network (SVM with Gaussian kernel and feature engineering and sequential convolutional network reach at best 36%). This serves as a proof of concept that neural networks can be valuable to study the properties of geometries appearing in string theory.

arXiv comment59 pages; additional details, references updated

References in corpus (76)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Practical Bayesian Optimization of Machine Learning Algorithms
• Geometric deep learning: going beyond Euclidean data
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Machine learning and the physical sciences
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Going Deeper with Convolutions
• A high-bias, low-variance introduction to Machine Learning for physicists
• Flux Compactification
• Flux compactifications in string theory: a comprehensive review
• Understanding Deep Convolutional Networks
• The statistics of string/M theory vacua
• A Model of Inductive Bias Learning
• Rethinking the Inception Architecture for Computer Vision
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Counting Flux Vacua
• Analyzing Inverse Problems with Invertible Neural Networks
• Computational complexity of the landscape I
• Basic results in Vacuum Statistics
• Machine Learning in the String Landscape
• Machine Learning of Calabi-Yau Volumes
• The Benefit of Multitask Representation Learning
• Monad Bundles in Heterotic String Compactifications
• Deep Learning and AdS/CFT
• Evolving neural networks with genetic algorithms to study the String Landscape
• Machine Learning CICY Threefolds
• The String Landscape, the Swampland, and the Missing Corner
• Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
• Fibrations in CICY Threefolds
• All Complete Intersection Calabi-Yau Four-Folds
• Deep Learning and Holographic QCD
• On Algorithmic Universality in F-theory Compactifications
• Topological Invariants and Fibration Structure of Complete Intersection Calabi-Yau Four-Folds
• Machine Learning Line Bundle Cohomologies of Hypersurfaces in Toric Varieties
• A New Construction of Calabi-Yau Manifolds: Generalized CICYs
• AdS/CFT as a deep Boltzmann machine
• Genetic Algorithms and the Search for Viable String Vacua
• Machine learning Calabi-Yau metrics
• Searching the Landscape of Flux Vacua with Genetic Algorithms
• Scanning the skeleton of the 4D F-theory landscape
• The F-theory geometry with most flux vacua
• Deep Learning and AdS/QCD
• Deep learning in the heterotic orbifold landscape
• Machine Learning Line Bundle Cohomology
• Computational Complexity of Vacua and Near-Vacua in Field and String Theory
• Holography as deep learning
• Getting CICY High
• Counting String Theory Standard Models
• SO(8) Supergravity and the Magic of Machine Learning
• The Role of Machine Learning in the Next Decade of Cosmology
• GANs for generating EFT models
• A Cornucopia of AdS${}_5$ Vacua
• Distinguishing Elliptic Fibrations with AI
• Deep learning black hole metrics from shear viscosity
• Machine Learning in High Energy Physics Community White Paper
• Machine Learning $\mathcal{N}=8,D=5$ Gauged Supergravity
• Estimating Calabi-Yau Hypersurface and Triangulation Counts with Equation Learners
• A new N=1 AdS4 Vacuum of Maximal Supergravity
• Inception Neural Network for Complete Intersection Calabi-Yau 3-folds
• Deep learning and k-means clustering in heterotic string vacua with line bundles
• Statistical Predictions in String Theory and Deep Generative Models
• Machine Learning and Algebraic Approaches towards Complete Matter Spectra in 4d F-theory
• Seeing through the String Landscape - a String Hunter's Companion in Particle Physics and Cosmology
• Learning non-Higgsable gauge groups in 4D F-theory
• Contrast data mining for the MSSM from strings
• Deep learning the holographic black hole with charge
• Machine Learning Etudes in Conformal Field Theories
• Predicting the orbifold origin of the MSSM
• Connecting Dualities and Machine Learning
• Generalization in multitask deep neural classifiers: a statistical physics approach
• Big Numbers in String Theory
• Calabi-Yau Spaces in the String Landscape
• Towards machine learning in the classification of Z2xZ2 orbifold compactifications

Cited by in corpus (18)

• The Calabi-Yau Landscape: from Geometry, to Physics, to Machine-Learning
• Machine Learning Calabi-Yau Hypersurfaces
• Machine Learning Calabi-Yau Four-folds
• Inception Neural Network for Complete Intersection Calabi-Yau 3-folds
• Applying machine learning to the Calabi-Yau orientifolds with string vacua
• Deep multi-task mining Calabi-Yau four-folds
• A Triumvirate of AI Driven Theoretical Discovery
• Unsupervised Machine Learning Techniques for Exploring Tropical Coamoeba, Brane Tilings and Seiberg Duality
• Machine learning Sasakian and $G_2$ topology on contact Calabi-Yau $7$-manifolds
• Machine Learning Regularization for the Minimum Volume Formula of Toric Calabi-Yau 3-folds
• Characterizing 4-string contact interaction using machine learning
• Deep learning complete intersection Calabi-Yau manifolds
• Universes as Big Data
• Machine Learning on generalized Complete Intersection Calabi-Yau Manifolds
• Constructing and Machine Learning Calabi-Yau Five-folds
• Metastable vacua from torsion and machine learning
• Black holes and the loss landscape in machine learning
• Machine learning of the well known things