Modal Backflow Neural Quantum States for Anharmonic Vibrational Calculations

Abstract

Neural quantum states (NQS) are a promising ansatz for solving many-body quantum problems due to their inherent expressiveness. Yet, this expressiveness can only be harnessed efficiently for treating identical particles if the suitable physical knowledge is hardwired into the neural network itself. For electronic structure, NQS based on backflow determinants has been shown to be a powerful ansatz for capturing strong correlation. By contrast, the analogue for bosons, backflow permanents, is unpractical due to the steep cost of computing the matrix permanent and due to the lack of particle conservation in common bosonic problems. To circumvent these obstacles, we introduce a modal backflow (MBF) NQS design and demonstrate its efficacy by solving the anharmonic vibrational problem. To accommodate the demand of high accuracy in spectroscopic calculations, we implement a selected-configuration scheme for evaluating physical observables and gradients, replacing the standard stochastic approach based on Monte Carlo sampling. A vibrational self-consistent field calculation is conveniently carried out within the MBF network, which serves as a pretraining step to accelerate and stabilize the optimization. In applications to both artificial and ab initio Hamiltonians, we find that the MBF network is capable of delivering spectroscopically accurate zero-point energies and vibrational transitions in all anharmonic regimes.

32 pages, 6 figures, 1 table

References in corpus (40)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Heat-bath Configuration Interaction: An efficient selected CI algorithm inspired by heat-bath sampling
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Quantum Entanglement in Neural Network States
• Multilayer multi-configuration time-dependent Hartree method: implementation and applications to a Henon-Heiles Hamiltonian and to pyrazine
• Quantum Monte Carlo method using phase-free random walks with Slater determinants
• The Density Matrix Renormalization Group in Chemistry and Molecular Physics: Recent Developments and New Challenges
• An adaptive configuration interaction approach for strongly correlated electrons with tunable accuracy
• Symmetries and many-body excited states with neural-network quantum states
• Fermionic neural-network states for ab-initio electronic structure
• Pushing Configuration-Interaction to the Limit: Towards Massively Parallel MCSCF Calculations
• Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
• NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems
• Ab-initio quantum chemistry with neural-network wavefunctions
• NetKet: A Machine Learning Toolkit for Many-Body Quantum Systems
• Role of backflow correlations for the non-magnetic phase of the t-t' Hubbard model
• Neural tensor contractions and the expressive power of deep neural quantum states
• Fermionic Wave Functions from Neural-Network Constrained Hidden States
• Computing vibrational eigenstates with tree tensor network states (TTNS)
• Vibrational Density Matrix Renormalization Group
• The Shape of Full Configuration Interaction to Come
• Accurate Computation of Quantum Excited States with Neural Networks
• Solving Quasiparticle Band Spectra of Real Solids using Neural-Network Quantum States
• Lifelong Machine Learning Potentials
• Optimization of highly excited matrix product states with an application to vibrational spectroscopy
• Excited states in variational Monte Carlo using a penalty method
• Nuclear-Electronic All-Particle Density Matrix Renormalization Group
• Flexible DMRG-based framework for anharmonic vibrational calculations
• Neural network backflow for ab-initio quantum chemistry
• Can neural quantum states learn volume-law ground states?
• A Non-stochastic Optimization Algorithm for Neural-network Quantum States
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?"
• Neural canonical transformations for vibrational spectra of molecules
• Tensor Network States for Vibrational Spectroscopy
• CoRe Optimizer: An All-in-One Solution for Machine Learning
• Benchmarking vibrational spectra: 5000 accurate eigenstates of acetonitrile using tree tensor network states
• Second-order optimisation strategies for neural network quantum states
• QCMaquis 4.0: Multi-Purpose Electronic, Vibrational, and Vibronic Structure and Dynamics Calculations with the Density Matrix Renormalization Group
• Finding the Dynamics of an Integrable Quantum Many-Body System via Machine Learning