Haldane Bundles: A Dataset for Learning to Predict the Chern Number of Line Bundles on the Torus (2312.04600v1)
Abstract: Characteristic classes, which are abstract topological invariants associated with vector bundles, have become an important notion in modern physics with surprising real-world consequences. As a representative example, the incredible properties of topological insulators, which are insulators in their bulk but conductors on their surface, can be completely characterized by a specific characteristic class associated with their electronic band structure, the first Chern class. Given their importance to next generation computing and the computational challenge of calculating them using first-principles approaches, there is a need to develop machine learning approaches to predict the characteristic classes associated with a material system. To aid in this program we introduce the {\emph{Haldane bundle dataset}}, which consists of synthetically generated complex line bundles on the $2$-torus. We envision this dataset, which is not as challenging as noisy and sparsely measured real-world datasets but (as we show) still difficult for off-the-shelf architectures, to be a testing ground for architectures that incorporate the rich topological and geometric priors underlying characteristic classes.
- Topological quantum chemistry. Nature, 547(7663):298–305, 2017.
- Shiing-shen Chern. Complex Manifolds with out Potential Theory. Springer, New York, 1979.
- Detection of topological materials with machine learning. Physical Review B, 101(24):245117, 2020.
- Fiber bundle morphisms as a framework for modeling many-to-many maps. In Topological, Algebraic and Geometric Learning Workshops 2022, pages 79–85. PMLR, 2022.
- Bundle networks: Fiber bundles, local trivializations, and a generative approach to exploring many-to-one maps. arXiv preprint arXiv:2110.06983, 2021.
- Daniel S Freed. Classical chern-simons theory, part 1. arXiv preprint hep-th/9206021, 1992.
- JE Gubernatis and T Lookman. Machine learning in materials design and discovery: Examples from the present and suggestions for the future. Physical Review Materials, 2(12):120301, 2018.
- F Duncan M Haldane. Model for a quantum hall effect without landau levels: Condensed-matter realization of the" parity anomaly". Physical review letters, 61(18):2015, 1988.
- Deep residual learning for image recognition. pages 770–778, 06 2016.
- An image is worth 16x16 words: Transformers for image recognition at scale. 2021.
- Panagiotis Kotetes. Topological insulators. Morgan & Claypool Publishers, 2019.
- Neural frames: A tool for studying the tangent bundles underlying image datasets and how deep learning models process them. arXiv preprint arXiv:2211.10558, 2022.
- Giant magnetochiral anisotropy from quantum-confined surface states of topological insulator nanowires. Nature Nanotechnology, 17(7):696–700, 2022.
- Surrounding sensitive electronic properties of bi2te3 nanoplates—potential sensing applications of topological insulators. Scientific Reports, 4(1):4639, 2014.
- Relative abundance of z 2 topological order in exfoliable two-dimensional insulators. Nano letters, 19(12):8431–8440, 2019.
- Characteristic classes. Number 76. Princeton university press, 1974.
- Rapid exploration of topological band structures using deep learning. Physical Review X, 11(2):021052, 2021.
- Machine learning for materials discovery: Two-dimensional topological insulators. Applied Physics Reviews, 8(3), 2021.
- Fibered: Fiberwise dimensionality reduction of topologically complex data with vector bundles. In 39th International Symposium on Computational Geometry (SoCG 2023). Schloss Dagstuhl-Leibniz-Zentrum für Informatik, 2023.
- Deep inside convolutional networks: Visualising image classification models and saliency maps. In Workshop at International Conference on Learning Representations, 2014.
- Geometrical engineering of a two-band chern insulator in two dimensions with arbitrary topological index. Physical Review B, 85(16), apr 2012.
- Edward Witten. Quantum field theory and the jones polynomial. Communications in Mathematical Physics, 121(3):351–399, 1989.
- Machine learning topological invariants with neural networks. Physical review letters, 120(6):066401, 2018.