Complete and Efficient Covariants for 3D Point Configurations with Application to Learning Molecular Quantum Properties

• URL: http://arxiv.org/abs/2409.02730v1
• Date: Wed, 4 Sep 2024 14:03:08 GMT
• Title: Complete and Efficient Covariants for 3D Point Configurations with Application to Learning Molecular Quantum Properties
• Abstract summary: We prove general completeness properties for higher order methods, and show that $6k-5$ of these features are enough for up to $k$ atoms. We apply this to quantum chemistry, but the proposed methods are generally applicable for problems involving 3D point configurations.
• Score: 17.093526789838567
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When modeling physical properties of molecules with machine learning, it is desirable to incorporate $SO(3)$-covariance. While such models based on low body order features are not complete, we formulate and prove general completeness properties for higher order methods, and show that $6k-5$ of these features are enough for up to $k$ atoms. We also find that the Clebsch--Gordan operations commonly used in these methods can be replaced by matrix multiplications without sacrificing completeness, lowering the scaling from $O(l^6)$ to $O(l^3)$ in the degree of the features. We apply this to quantum chemistry, but the proposed methods are generally applicable for problems involving 3D point configurations.

Related papers

• Perturbation theory, irrep truncations, and state preparation methods for quantum simulations of SU(3) lattice gauge theory [0.0]
  We study methods for efficient preparation of approximate ground states of $SU(3)$ lattice gauge theory on quantum hardware.<n>We develop simple ansatz circuits for ground state preparation and test them via classical simulation on small lattices.
  arXiv  Detail & Related papers  (2025-09-30T07:01:26Z)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [90.23688195918432]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• Scaling Gaussian Processes for Learning Curve Prediction via Latent Kronecker Structure [16.319561844942886]
  We show that our GP model can match the performance of a Transformer on a learning curve prediction task. Our method only requires $mathcalO(n3 + m3)$ time and $mathcalO(n2 + m2)$ space.
  arXiv  Detail & Related papers  (2024-10-11T20:24:33Z)
• Fast, Expressive SE$(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space [15.495593104596399]
  We formalize the notion of weight sharing in convolutional networks as the sharing of message functions over point-pairs. We develop an efficient equivariant group convolutional network for processing 3D point clouds.
  arXiv  Detail & Related papers  (2023-10-04T17:06:32Z)
• Automated 3D Pre-Training for Molecular Property Prediction [54.15788181794094]
  We propose a novel 3D pre-training framework (dubbed 3D PGT) It pre-trains a model on 3D molecular graphs, and then fine-tunes it on molecular graphs without 3D structures. Extensive experiments on 2D molecular graphs are conducted to demonstrate the accuracy, efficiency and generalization ability of the proposed 3D PGT.
  arXiv  Detail & Related papers  (2023-06-13T14:43:13Z)
• Hydrogen atom confined inside an inverted-Gaussian potential [0.0]
  In particular, this model has been used to study atoms inside a $C_60$ fullerene. Results with not less than 11 significant figures are displayed.
  arXiv  Detail & Related papers  (2022-08-28T00:38:24Z)
• Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation [4.061135251278187]
  We show that a wide range of kernels gives rise to structured matrices, enabling an exact $mathcalO(n2d)$ matrix-vector multiply for gradient observations and $mathcalO(n2d2)$ for Hessian observations. Our methods apply to virtually all canonical kernels and automatically extend to complex kernels, like the neural network, radial basis function network, and spectral mixture kernels.
  arXiv  Detail & Related papers  (2022-06-16T17:59:48Z)
• Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs [79.06686274377009]
  We develop a benchmark, known as Molecule3D, that includes a dataset with precise ground-state geometries of approximately 4 million molecules. We implement two baseline methods that either predict the pairwise distance between atoms or atom coordinates in 3D space. Our method can achieve comparable prediction accuracy but with much smaller computational costs.
  arXiv  Detail & Related papers  (2021-09-30T22:09:28Z)
• Variational quantum algorithm for molecular geometry optimization [0.0]
  We introduce a variational quantum algorithm for finding the most stable structure of a molecule. The equilibrium geometry of the molecule is obtained by minimizing a more general cost function. All quantum simulations are performed using the PennyLane library for quantum differentiable programming.
  arXiv  Detail & Related papers  (2021-06-25T18:34:44Z)
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles [60.12186997181117]
  Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements. We propose GeoMol, an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate 3D conformers.
  arXiv  Detail & Related papers  (2021-06-08T14:17:59Z)
• High-Dimensional Gaussian Process Inference with Derivatives [90.8033626920884]
  We show that in the low-data regime $ND$, the Gram matrix can be decomposed in a manner that reduces the cost of inference to $mathcalO(N2D + (N2)3)$. We demonstrate this potential in a variety of tasks relevant for machine learning, such as optimization and Hamiltonian Monte Carlo with predictive gradients.
  arXiv  Detail & Related papers  (2021-02-15T13:24:41Z)
• Even more efficient quantum computations of chemistry through tensor hypercontraction [0.6234350105794442]
  We describe quantum circuits with only $widetildecal O(N)$ Toffoli complexity that block encode the spectra of quantum chemistry Hamiltonians in a basis of $N$ arbitrary orbitals. This is the lowest complexity that has been shown for quantum computations of chemistry within an arbitrary basis.
  arXiv  Detail & Related papers  (2020-11-06T18:03:29Z)
• Four-Dimensional Scaling of Dipole Polarizability in Quantum Systems [55.54838930242243]
  Polarizability is a key response property of physical and chemical systems. We show that polarizability follows a universal four-dimensional scaling law. This formula is also applicable to many-particle systems.
  arXiv  Detail & Related papers  (2020-10-22T15:42:36Z)
• Variational Monte Carlo calculations of $\mathbf{A\leq 4}$ nuclei with an artificial neural-network correlator ansatz [62.997667081978825]
  We introduce a neural-network quantum state ansatz to model the ground-state wave function of light nuclei. We compute the binding energies and point-nucleon densities of $Aleq 4$ nuclei as emerging from a leading-order pionless effective field theory Hamiltonian.
  arXiv  Detail & Related papers  (2020-07-28T14:52:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.