Convergence of variational Monte Carlo simulation and scale-invariant pre-training

Abstract

We provide theoretical convergence bounds for the variational Monte Carlo (VMC) method as applied to optimize neural network wave functions for the electronic structure problem. We study both the energy minimization phase and the supervised pre-training phase that is commonly used prior to energy minimization. For the energy minimization phase, the standard algorithm is scale-invariant by design, and we provide a proof of convergence for this algorithm without modifications. The pre-training stage typically does not feature such scale-invariance. We propose using a scale-invariant loss for the pretraining phase and demonstrate empirically that it leads to faster pre-training.

Update to JCP version

References in corpus (17)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Generalized Lanczos Algorithm for Variational Quantum Monte Carlo
• Stochastic gradient descent on Riemannian manifolds
• Optimization of quantum Monte Carlo wave functions by energy minimization
• Green Function Monte Carlo with Stochastic Reconfiguration
• Fermionic neural-network states for ab-initio electronic structure
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Variational quantum Monte Carlo simulations with tensor-network states
• Optimizing large parameter sets in variational quantum Monte Carlo
• Optimization of ground and excited state wavefunctions and van der Waals clusters
• Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport
• Ab initio calculation of real solids via neural network ansatz
• Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
• Complementary First and Second Derivative Methods for Ansatz Optimization in Variational Monte Carlo