Towards a Foundation Model for Neural Network Wavefunctions
- URL: http://arxiv.org/abs/2303.09949v1
- Date: Fri, 17 Mar 2023 16:03:10 GMT
- Title: Towards a Foundation Model for Neural Network Wavefunctions
- Authors: Michael Scherbela, Leon Gerard, Philipp Grohs
- Abstract summary: We propose a novel neural network ansatz, which maps uncorrelated, computationally cheap Hartree-Fock orbitals to correlated, high-accuracy neural network orbitals.
This ansatz is inherently capable of learning a single wavefunction across multiple compounds and geometries.
- Score: 5.145741425164946
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep neural networks have become a highly accurate and powerful wavefunction
ansatz in combination with variational Monte Carlo methods for solving the
electronic Schr\"odinger equation. However, despite their success and favorable
scaling, these methods are still computationally too costly for wide adoption.
A significant obstacle is the requirement to optimize the wavefunction from
scratch for each new system, thus requiring long optimization. In this work, we
propose a novel neural network ansatz, which effectively maps uncorrelated,
computationally cheap Hartree-Fock orbitals, to correlated, high-accuracy
neural network orbitals. This ansatz is inherently capable of learning a single
wavefunction across multiple compounds and geometries, as we demonstrate by
successfully transferring a wavefunction model pre-trained on smaller fragments
to larger compounds. Furthermore, we provide ample experimental evidence to
support the idea that extensive pre-training of a such a generalized
wavefunction model across different compounds and geometries could lead to a
foundation wavefunction model. Such a model could yield high-accuracy ab-initio
energies using only minimal computational effort for fine-tuning and evaluation
of observables.
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) - Physics-informed neural wavefields with Gabor basis functions [4.07926531936425]
We propose an approach to enhance the efficiency and accuracy of neural network wavefield solutions.
Specifically, for the Helmholtz equation, we augment the fully connected neural network model with an Gabor layer constituting the final hidden layer.
These/coefficients of the Gabor functions are learned from the previous hidden layers that include nonlinear activation functions.
arXiv Detail & Related papers (2023-10-16T17:30:33Z) - Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave
Functions [2.61072980439312]
In this work, we combine a Graph Neural Network (GNN) with a neural wave function to simultaneously solve the Schr"odinger equation for multiple geometries via VMC.
Compared to existing state-of-the-art networks, our Potential Energy Surface Network (PESNet) speeds up training for multiple geometries by up to 40 times while matching or surpassing their accuracy.
arXiv Detail & Related papers (2021-10-11T07:58:31Z) - 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) - Autoencoder-driven Spiral Representation Learning for Gravitational Wave
Surrogate Modelling [47.081318079190595]
We investigate the existence of underlying structures in the empirical coefficients using autoencoders.
We design a spiral module with learnable parameters, that is used as the first layer in a neural network, which learns to map the input space to the coefficients.
The spiral module is evaluated on multiple neural network architectures and consistently achieves better speed-accuracy trade-off than baseline models.
arXiv Detail & Related papers (2021-07-09T09:03:08Z) - 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) - 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) - Measuring Model Complexity of Neural Networks with Curve Activation
Functions [100.98319505253797]
We propose the linear approximation neural network (LANN) to approximate a given deep model with curve activation function.
We experimentally explore the training process of neural networks and detect overfitting.
We find that the $L1$ and $L2$ regularizations suppress the increase of model complexity.
arXiv Detail & Related papers (2020-06-16T07:38:06Z) - Flexible Transmitter Network [84.90891046882213]
Current neural networks are mostly built upon the MP model, which usually formulates the neuron as executing an activation function on the real-valued weighted aggregation of signals received from other neurons.
We propose the Flexible Transmitter (FT) model, a novel bio-plausible neuron model with flexible synaptic plasticity.
We present the Flexible Transmitter Network (FTNet), which is built on the most common fully-connected feed-forward architecture.
arXiv Detail & Related papers (2020-04-08T06:55:12Z) - Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model.
This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs)
The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
arXiv Detail & Related papers (2020-03-13T13:11:35Z)
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.