Accurate Computation of Quantum Excited States with Neural Networks

Abstract

We present a variational Monte Carlo algorithm for estimating the lowest excited states of a quantum system which is a natural generalization of the estimation of ground states. The method has no free parameters and requires no explicit orthogonalization of the different states, instead transforming the problem of finding excited states of a given system into that of finding the ground state of an expanded system. Expected values of arbitrary observables can be calculated, including off-diagonal expectations between different states such as the transition dipole moment. Although the method is entirely general, it works particularly well in conjunction with recent work on using neural networks as variational Ansätze for many-electron systems, and we show that by combining this method with the FermiNet and Psiformer Ansätze we can accurately recover vertical excitation energies and oscillator strengths on a range of molecules. Our method is the first deep learning approach to achieve accurate vertical excitation energies, including challenging double excitations, on benzene-scale molecules. Beyond the chemistry examples here, we expect this technique will be of great interest for applications to atomic, nuclear and condensed matter physics.

The content of this version is identical to the manuscript draft which was sent to Science on May 17th 2024

References in corpus (10)

• QUESTDB: a database of highly-accurate excitation energies for the electronic structure community
• Excited states using semistochastic heat-bath configuration interaction
• Ab-initio quantum chemistry with neural-network wavefunctions
• Targeted Excited State Algorithms
• Ab initio calculation of real solids via neural network ansatz
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas
• A Mountaineering Strategy to Excited States: Revising Reference Values with EOM-CC4
• Deep-neural-network approach to solving the ab initio nuclear structure problem
• Tailoring CIPSI expansions for QMC calculations of electronic excitations: the case study of thiophene
• Optical Spectroscopy of Comet C/2014 Q2 (Lovejoy) from MIRO

Cited by in corpus (12)

• The QUEST Database of Highly-Accurate Excitation Energies
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
• Is attention all you need to solve the correlated electron problem?
• Machine learning of phases and structures for model systems in physics
• Deep quantum Monte Carlo approach for polaritonic chemistry
• Physics-informed Transformers for Electronic Quantum States
• Bound on entanglement in neural quantum states
• Modal Backflow Neural Quantum States for Anharmonic Vibrational Calculations
• Machine learning the single-$\Lambda$ hypernuclei with neural-network quantum states
• Imaginary Time Spectral Transforms for Excited State Preparation