We overview similarities and, importantly, differences in computational bottlenecks and accuracy requirements that can be addressed with machine learning (ML) and artificial intelligence (AI) techniques in electronic and nuclear DFT. From these follow different promising methodological and algorithmic choices depending on whether one machine learns the exchange correlation (XC) functional, the kinetic energy functional (KEF), the density or the basis functions. In particular, while the popular deep neural networks remain a potent choice in the context of KS DFT, we highlight their disadvantages when building KEFs and highlight conceptual advantages - yet to be fully realized - of symbolic regression for both electronic and nuclear DFT. We point out promising approaches that can be carried from the more extensively investigated ML-enhanced electronic DFT to nuclear DFT.
We overview similarities and, importantly, differences in computational bottlenecks and accuracy requirements that can be addressed with machine learning (ML) and artificial intelligence (AI) techniques in electronic and nuclear DFT. From these follow different promising methodological and algorithmic choices depending on whether one machine learns the exchange correlation (XC) functional, the kinetic energy functional (KEF), the density or the basis functions. In particular, while the popular deep neural networks remain a potent choice in the context of KS DFT, we highlight their disadvantages when building KEFs and highlight conceptual advantages - yet to be fully realized - of symbolic regression for both electronic and nuclear DFT. We point out promising approaches that can be carried from the more extensively investigated ML-enhanced electronic DFT to nuclear DFT.
Kohn-Sham density functional theory (KS-DFT) provides the exact ground-state energy and electron density of a molecule, contingent on the as-yet-unknown universal exchange-correlation (XC) functional. Recent research has demonstrated that neural networks can efficiently learn to represent approximations to that functional, offering accurate generalizations to molecules not present during the training process. With the latest advancements in quantum-enhanced machine learning (ML), evidence is growing that quantum neural network (QNN) models may offer advantages in ML applications. In this work, we explore the use of QNNs for representing XC functionals, enhancing and comparing them to classical ML techniques. We present QNNs based on differentiable quantum circuits as quantum (hybrid) models for XC in KS-DFT, implemented across various architectures. We assess their performance on one-dimensional (1D) and 3D systems. To that end, we expand existing differentiable KS-DFT frameworks and propose strategies for efficient training of such functionals, highlighting the importance of fractional orbital occupation for accurate results. We prove that, under specific assumptions, noise-induced errors do not accumulate across SCF iterations, and we confirm this result through numerical experiments. Our best QNN-based XC functional yields energy profiles of the H 2 and planar H 4 molecules that deviate by no more than 1 mHa from the reference DMRG and FCI/6-31G results, respectively. Moreover, they reach chemical precision on a system, H 2 H 2 , not present in the training dataset, using only a few variational parameters. This work lays the foundation for the integration of quantum models in KS-DFT, thereby opening new avenues for expressing XC functionals in a differentiable way and facilitating computations of various properties.
Density functional theory underlies the most successful and widely used numerical methods for electronic structure prediction of solids. However, it has the fundamental shortcoming that the universal density functional is unknown. In addition, the computational result—energy and charge density distribution of the ground state—is useful for electronic properties of solids mostly when reduced to a band structure interpretation based on the Kohn-Sham approach. Here, we demonstrate how machine learning algorithms can help to free density functional theory from these limitations. We study a theory of spinless fermions on a one-dimensional lattice. The density functional is implicitly represented by a neural network, which predicts, besides the ground-state energy and density distribution, density-density correlation functions. At no point do we require a band structure interpretation. The training data, obtained via exact diagonalization, feeds into a learning scheme inspired by active learning, which minimizes the computational costs for data generation. We show that the network results are of high quantitative accuracy and, despite learning on random potentials, capture both symmetry-breaking and topological phase transitions correctly.
Density functional theory underlies the most successful and widely used numerical methods for electronic structure prediction of solids. However, it has the fundamental shortcoming that the universal density functional is unknown. In addition, the computational result---energy and charge density distribution of the ground state---is useful for electronic properties of solids mostly when reduced to a band structure interpretation based on the Kohn-Sham approach. Here, we demonstrate how machine learning algorithms can help to free density functional theory from these limitations. We study a theory of spinless fermions on a one-dimensional lattice. The density functional is implicitly represented by a neural network, which predicts, besides the ground-state energy and density distribution, density-density correlation functions. At no point do we require a band structure interpretation. The training data, obtained via exact diagonalization, feeds into an active learning scheme which minimizes the computational costs for data generation. We show that the network results are of high quantitative accuracy and, despite learning on random potentials, capture both symmetry-breaking and topological phase transitions correctly.
Abstract The construction of a better exchange-correlation potential in time-dependent density functional theory (TDDFT) can improve the accuracy of TDDFT calculations and provide more accurate predictions of the properties of many-electron systems. Here, we propose a machine learning method to develop the energy functional and the Kohn–Sham potential of a time-dependent Kohn–Sham (TDKS) system is proposed. The method is based on the dynamics of the Kohn–Sham system and does not require any data on the exact Kohn–Sham potential for training the model. We demonstrate the results of our method with a 1D harmonic oscillator example and a 1D two-electron example. We show that the machine-learned Kohn–Sham potential matches the exact Kohn–Sham potential in the absence of memory effect. Our method can still capture the dynamics of the Kohn–Sham system in the presence of memory effects. The machine learning method developed in this article provides insight into making better approximations of the energy functional and the Kohn–Sham potential in the TDKS system.
Hybrid artificial intelligence–quantum (AI–Q) models arise at the intersection of two rapidly advancing computational paradigms, promising unprecedented capabilities for real-time molecular structure prediction. In classical computational chemistry, the accurate determination of ground-state energies and optimized geometries relies on ab initio methods such as density functional theory (DFT) and coupled-cluster approaches, which, while highly precise, exhibit steep polynomial or exponential scaling with system size. Conversely, deep neural networks (DNNs) have demonstrated remarkable success in learning potential energy surfaces (PES) from large datasets, achieving rapid inference but sometimes lacking the ultimate chemical accuracy required for predictive applications in drug discovery or materials design. On the other hand, variational quantum eigensolvers (VQEs) leverage the intrinsic parallelism of quantum hardware to approximate electronic structure problems, yet they remain constrained by qubit coherence times, gate fidelities, and circuit depth limitations inherent to noisy intermediate-scale quantum (NISQ) devices.
While quantum computers have shown significant promise for electronic structure calculations, their potential to accelerate density functional theory (DFT) calculations remains unclear. In this work, we present a qubit-efficient encoding scheme for wavefunctions in Kohn--Sham (KS) DFT, together with a quantum algorithm that computes all occupied orbitals simultaneously. We further show that our algorithm is particularly well suited to the Harris functional, enabling the total energy to be evaluated with a potential exponential speedup over classical approaches by entirely avoiding the costly readout of the electronic density. In addition, we propose a second method for achieving self-consistent DFT calculations using multiple copies of the wavefunction, which likewise circumvents density readout. The applicability of our algorithms is demonstrated through several numerical examples, and their efficiency is compared with that of existing approaches.