Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Atomic Cluster Expansion without Self-Interaction (2401.01550v2)

Published 3 Jan 2024 in math.NA, cs.NA, and physics.comp-ph

Abstract: The Atomic Cluster Expansion (ACE) (Drautz, Phys. Rev. B 99, 2019) has been widely applied in high energy physics, quantum mechanics and atomistic modeling to construct many-body interaction models respecting physical symmetries. Computational efficiency is achieved by allowing non-physical self-interaction terms in the model. We propose and analyze an efficient method to evaluate and parameterize an orthogonal, or, non-self-interacting cluster expansion model. We present numerical experiments demonstrating improved conditioning and more robust approximation properties than the original expansion in regression tasks both in simplified toy problems and in applications in the machine learning of interatomic potentials.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. ACE1x.jl. Experimental features for ACEpotentials.jl. github.com/ACEsuit/ACE1x.jl.
  2. ACEpotentials.jl. Documentation and user interface for Julia-language development of ACE potentials. github.com/ACEsuit/ACEpotentials.jl.
  3. Polynomial approximation of symmetric functions. arXiv:2109.14771, 2023. to appear in Math. Comput.
  4. The design space of E(3)-equivariant atom-centered interatomic potentials. arXiv:2205.06643, 2022. to appear in Nature Machine Intelligence.
  5. A general framework for equivariant neural networks on reductive Lie groups. arXiv:2306.00091, 2023. to appear in Advances in Neural Information Processing Systems.
  6. Mace: Higher order equivariant message passing neural networks for fast and accurate force fields. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Adv. Neural Inf. Process. Syst., volume 35, pages 11423–11436. Curran Associates, Inc., 2022.
  7. Equivariant matrix function neural networks. arXiv:2310.10434, 2023.
  8. Machine learning and invariant theory. arXiv:2209.14991, 2023.
  9. Permutationally invariant potential energy surfaces in high dimensionality. Int. Rev. Phys. Chem., 28(4):577–606, 2009.
  10. William Elwood Byerly. An elemenatary treatise on Fourier’s series, and spherical, cylindrical, and ellipsoidal harmonics, with applications to problems in mathematical physics. Dover Publications, 1893.
  11. Qm/mm methods for crystalline defects. part 1: Locality of the tight binding model. Multiscale Model. Sim., 14(1):232–264, 2016.
  12. On the stability and accuracy of least squares approximations. Found. Comput. Math., 13:819–834, 2013.
  13. Machine learning interatomic potentials as emerging tools for materials science. Advanced Materials, 31(46):1902765, 2019.
  14. Ralf Drautz. Atomic cluster expansion for accurate and transferable interatomic potentials. Phys. Rev. B, 99:014104, Jan 2019.
  15. Atomic cluster expansion and wave function representations. arXiv:2206.11375, 2022.
  16. Atomic cluster expansion: Completeness, efficiency and stability. J. Comput. Phys., 454:110946, 2022.
  17. George Gasper. Linearization of the product of Jacobi polynomials. I. Canadian J. Math., 22(1):171–175, 1970.
  18. Geometric deep learning and equivariant neural networks. Artif. Intell. Rev., pages 1–58, 2023.
  19. Pascal Giorgi. On polynomial multiplication in Chebyshev basis. IEEE Trans. Comput., 61(6):780–789, 2011.
  20. Lietransformer: Equivariant self-attention for Lie groups. In International Conference on Machine Learning, pages 4533–4543. PMLR, 2021.
  21. Evaluation of the MACE force field architecture: from medicinal chemistry to materials science. J. Chem. Phys., 159(4), jul 2023.
  22. Linear atomic cluster expansion force fields for organic molecules: beyond rmse. J. Chem. Theory Comput., 17(12):7696–7711, 2021.
  23. Set transformer: A framework for attention-based permutation-invariant neural networks. In International Conference on Machine Learning, pages 3744–3753. PMLR, 2019.
  24. Deep-learning density functional theory hamiltonian for efficient ab initio electronic-structure calculation. Nat. Comput. Sci., 2(6):367–377, 2022.
  25. Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon. npj Comput. Mater., 7(1):97, 2021.
  26. Boost invariant polynomials for efficient jet tagging. Mach. Learn.: Sci. Technol., 3(4):04LT05, 2022.
  27. Physics-inspired structural representations for molecules and materials. Chemical Reviews, 121(16):9759–9815, 2021.
  28. Recursive evaluation and iterative contraction of n-body equivariant features. J. Chem. Phys., 153(12), 2020.
  29. Locality of interatomic forces in tight binding models for insulators. ESAIM: Mathematical Modelling and Numerical Analysis, 54(6):2295–2318, 2020.
  30. Atomic cluster expansion for quantum-accurate large-scale simulations of carbon. J. Chem. Theory Comput., 19(15):5151–5167, 2023.
  31. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Adv. Neural Inf. Process. Syst., volume 30. Curran Associates, Inc., 2017.
  32. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv:1802.08219, 2018.
  33. Lloyd N. Trefethen. Multivariate polynomial approximation in the hypercube. Proc. Amer. Math. Soc., 145(11):4837–4844, 2017.
  34. Regularised atomic body-ordered permutation-invariant polynomials for the construction of interatomic potentials. Mach. Learn.: Sci. Technol., 1(1):015004, 2020.
  35. Hyperactive learning for data-driven interatomic potentials. npj Computational Materials, 9(1):168, 2023.
  36. On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events. npj Comput. Mater., 6(1):20, 2020.
  37. A theoretical case study of the generalisation of machine-learned potentials. arXiv:2311.01664, 2023.
  38. Acepotentials. jl: A julia implementation of the atomic cluster expansion. J. Chem. Phys., 159(16), 2023.
  39. Mathematical apparatus of the theory of angular momentum. Academy of Sciences of the Lithuanian S.S.R., 1962.
  40. Atomistic fracture in bcc iron revealed by active learning of gaussian approximation potential. npj Computational Materials, 9(1):217, Dec 2023.
  41. Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models. npj Comput. Mater., 8(1):158, 2022.
  42. A multilevel method for many-electron Schrödinger equations based on the atomic cluster expansion. arXiv:2304.04260, 2023. to appear in SIAM J. Sci. Comput.
  43. Performance and cost assessment of machine learning interatomic potentials. J. Phys. Chem. A, 124(4):731–745, 2020. PMID: 31916773.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now