A Self-Attention Ansatz for Ab-initio Quantum Chemistry
- URL: http://arxiv.org/abs/2211.13672v2
- Date: Wed, 19 Apr 2023 06:13:02 GMT
- Title: A Self-Attention Ansatz for Ab-initio Quantum Chemistry
- Authors: Ingrid von Glehn, James S. Spencer, David Pfau
- Abstract summary: We present a novel neural network architecture using self-attention, the Wavefunction Transformer (Psiformer)
We show that the Psiformer can be used as a drop-in replacement for other neural networks, often dramatically improving the accuracy of the calculations.
This demonstrates that self-attention networks can learn complex quantum mechanical correlations between electrons, and are a promising route to reaching unprecedented accuracy in chemical calculations on larger systems.
- Score: 3.4161707164978137
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We present a novel neural network architecture using self-attention, the
Wavefunction Transformer (Psiformer), which can be used as an approximation (or
Ansatz) for solving the many-electron Schr\"odinger equation, the fundamental
equation for quantum chemistry and material science. This equation can be
solved from first principles, requiring no external training data. In recent
years, deep neural networks like the FermiNet and PauliNet have been used to
significantly improve the accuracy of these first-principle calculations, but
they lack an attention-like mechanism for gating interactions between
electrons. Here we show that the Psiformer can be used as a drop-in replacement
for these other neural networks, often dramatically improving the accuracy of
the calculations. On larger molecules especially, the ground state energy can
be improved by dozens of kcal/mol, a qualitative leap over previous methods.
This demonstrates that self-attention networks can learn complex quantum
mechanical correlations between electrons, and are a promising route to
reaching unprecedented accuracy in chemical calculations on larger systems.
Related papers
- Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations [58.130170155147205]
Neural wave functions accomplished unprecedented accuracies in approximating the ground state of many-electron systems, though at a high computational cost.
Recent works proposed amortizing the cost by learning generalized wave functions across different structures and compounds instead of solving each problem independently.
This work tackles the problem by defining overparametrized, fully learnable neural wave functions suitable for generalization across molecules.
arXiv Detail & Related papers (2024-05-23T16:30:51Z) - Modeling Non-Covalent Interatomic Interactions on a Photonic Quantum
Computer [50.24983453990065]
We show that the cQDO model lends itself naturally to simulation on a photonic quantum computer.
We calculate the binding energy curve of diatomic systems by leveraging Xanadu's Strawberry Fields photonics library.
Remarkably, we find that two coupled bosonic QDOs exhibit a stable bond.
arXiv Detail & Related papers (2023-06-14T14:44:12Z) - Ab-initio quantum chemistry with neural-network wavefunctions [2.3306857544105686]
Key application of machine learning in the molecular sciences is to learn potential energy surfaces or force fields.
We focus on quantum Monte Carlo (QMC) methods that use neural network ansatz functions in order to solve the electronic Schr"odinger equation.
arXiv Detail & Related papers (2022-08-26T11:33:31Z) - Nuclear two point correlation functions on a quantum-computer [105.89228861548395]
We use current quantum hardware and error mitigation protocols to calculate response functions for a highly simplified nuclear model.
In this work we use current quantum hardware and error mitigation protocols to calculate response functions for a modified Fermi-Hubbard model in two dimensions with three distinguishable nucleons on four lattice sites.
arXiv Detail & Related papers (2021-11-04T16:25:33Z) - Autoregressive neural-network wavefunctions for ab initio quantum
chemistry [3.5987961950527287]
We parameterise the electronic wavefunction with a novel autoregressive neural network (ARN)
This allows us to perform electronic structure calculations on molecules with up to 30 spin-orbitals.
arXiv Detail & Related papers (2021-09-26T13:44:41Z) - Computing molecular excited states on a D-Wave quantum annealer [52.5289706853773]
We demonstrate the use of a D-Wave quantum annealer for the calculation of excited electronic states of molecular systems.
These simulations play an important role in a number of areas, such as photovoltaics, semiconductor technology and nanoscience.
arXiv Detail & Related papers (2021-07-01T01:02:17Z) - SE(3)-equivariant prediction of molecular wavefunctions and electronic
densities [4.2572103161049055]
We introduce general SE(3)-equivariant operations and building blocks for constructing deep learning architectures for geometric point cloud data.
Our model reduces prediction errors by up to two orders of magnitude compared to the previous state-of-the-art.
We demonstrate the potential of our approach in a transfer learning application, where a model trained on low accuracy reference wavefunctions implicitly learns to correct for electronic many-body interactions.
arXiv Detail & Related papers (2021-06-04T08:57:46Z) - Solving the electronic Schr\"odinger equation for multiple nuclear
geometries with weight-sharing deep neural networks [4.1201966507589995]
We introduce a weight-sharing constraint when optimizing neural network-based models for different molecular geometries.
We find that this technique can accelerate optimization when considering sets of nuclear geometries of the same molecule by an order of magnitude.
arXiv Detail & Related papers (2021-05-18T08:23:09Z) - Electronic structure with direct diagonalization on a D-Wave quantum
annealer [62.997667081978825]
This work implements the general Quantum Annealer Eigensolver (QAE) algorithm to solve the molecular electronic Hamiltonian eigenvalue-eigenvector problem on a D-Wave 2000Q quantum annealer.
We demonstrate the use of D-Wave hardware for obtaining ground and electronically excited states across a variety of small molecular systems.
arXiv Detail & Related papers (2020-09-02T22:46:47Z) - 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.