Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Russian Journal of Physical Chemistry A

Applying the Monte Carlo Method to Problems of Modeling Stationary States of Quantum Systems by Means of Machine Learning

Georgiy K. Ozerov, Aleksandr K. Pupeza, Dmitry S. Bezrukov

Published Oct 28, 2025• 0 citations
Publisher

Abstract

Abstract An overview is presented of recent advances in applying variational, projection, and diffusion Monte Carlo methods (VMC, PMC, and DMC, respectively). The prospects for using the Monte Carlo method to calculate path integrals (PIMC) when modeling molecular systems are also considered. It is emphasized that modern machine learning effectively meets the requirements of parameterizing wave functions of the target space of solutions for a wide range of problems in quantum molecular modeling and functionals of the corresponding observables.

DOI
10.1134/s0036024425702188

Related papers

Excited‐State Calculations with Quantum Monte Carlo

Jonas Feldt, Claudia Filippi

Quantum Monte Carlo methods are first-principle approaches that approximately solve the Schrödinger equation stochastically. As compared to traditional quantum chemistry methods, they offer important advantages such as the ability to handle a large variety of many-body wave functions, the favorable scaling with the number of particles, and the intrinsic parallelism of the algorithms which are particularly suitable to modern massively parallel computers. In this chapter, we focus on the two quantum Monte Carlo approaches most widely used for electronic structure problems, namely, the variational and diffusion Monte Carlo methods. We give particular attention to the recent progress in the techniques for the optimization of the wave function, a challenging and important step to achieve accurate results in both the ground and the excited state. We conclude with an overview of the current status of excited-state calculations for molecular systems, demonstrating the potential of quantum Monte Carlo methods in this field of applications.

arXiv:2002.03622•Wiley eBooks•Nov 23, 2020•19 citations

Quantum Monte Carlo methods

Joseph Marie Thijssen

Introduction In Chapters 1 to 4 we studied methods for solving the Schrödinger equation for many-electron systems. Many of the techniques described there carry over to other quantum many-particle systems, such as liquid helium, and the protons and neutrons in a nucleus. The techniques which we discussed there were, however, all of a mean-field type and therefore correlation effects could not be taken into account without introducing approximations. In this chapter, we consider more accurate techniques, which are similar to those studied in Chapter 10 and are based on using (pseudo-)random numbers – hence the name ‘Monte Carlo’ for these methods. In Chapter 10 we applied Monte Carlo techniques to classical many-particle systems; here we use these techniques for studying quantum problems involving many particles. In the next section we shall see how we can apply Monte Carlo techniques to the problem of calculating the quantum mechanical expectation value of the ground state energy. This is used in order to optimise this expectation value by adjusting a trial wave function in a variational type of approach, hence the name variational Monte Carlo (VMC). In the following section we use the similarity between the Schrödinger equation and the diffusion equation in order to calculate the properties of a collection of interacting quantum mechanical particles by simulating a classical particle diffusion process. The resulting method is called diffusion Monte Carlo (DMC).

Cambridge University Press eBooks•Mar 22, 2007•26 citations

Applications of the Fixed-Node Quantum Monte Carlo Method

Adem Halil Kulahlioglu

KULAHLIOGLU, ADEM HALIL.Applications of the Fixed-Node Quantum Monte Carlo Method.(Under the direction of Lubos Mitas.)Quantum Monte Carlo (QMC) is a highly sophisticated quantum many-body method.Diffusion Monte Carlo (DMC), a projected QMC method, is a stochastic solution of the stationary Schrödinger's equation.It is, in principle, an exact method.However, in dealing with fermions, since trial wave functions meet the antisymmetric condition of the many-body fermionic systems, it inevitably encounters the fermion sign problem.One of the ways to circumvent the sign problem is by imposing the so-called fixed-node approximation.The fixed-node DMC (FN-DMC), a highly promising method, is emerging as the method

•Oct 31, 2014•0 citations

Path-integral diffusion Monte Carlo: Calculation of observables of many-body systems in the ground state

Balázs Hetényi, Eran Rabani, B. J. Berne

We propose a new method to calculate ground state position dependent observables in quantum many-body systems. The method, which we call the path-integral diffusion Monte Carlo (PI-DMC) method, is essentially a combination of path-integral Monte Carlo (PIMC) and diffusion Monte Carlo (DMC) methods. The distribution resulting from a DMC simulation is further propagated in imaginary time by PIMC sampling. Tests of the new method for simple cases such as the harmonic oscillator, a double well, and a set of ten coupled harmonic oscillators show that the results for several observables converge rapidly to the exact result.

The Journal of Chemical Physics•Apr 1, 1999•21 citations

Machine-learning quantum mechanics: Solving quantum mechanics problems using radial basis function networks

Peiyuan Teng

In this article, machine-learning methods are used to solve quantum mechanics problems. The radial basis function network in a discrete basis is used as the variational wave function for the ground state of a quantum system. Variational Monte Carlo (VMC) calculations are carried out for some simple Hamiltonians. The results are in good agreement with theoretical values. The smallest eigenvalue of a Hermitian matrix can also be acquired using VMC calculations. Results are provided to demonstrate that machine-learning techniques are capable of solving quantum mechanical problems.

arXiv:1710.03213•Physical review. E•Sep 14, 2018•37 citations

DeepQMC: An open-source software suite for variational optimization of deep-learning molecular wave functions

Zeno Schätzle, P. Bernát Szabó, Matěj Mezera +2 more

Computing accurate yet efficient approximations to the solutions of the electronic Schrödinger equation has been a paramount challenge of computational chemistry for decades. Quantum Monte Carlo methods are a promising avenue of development as their core algorithm exhibits a number of favorable properties: it is highly parallel and scales favorably with the considered system size, with an accuracy that is limited only by the choice of the wave function Ansatz. The recently introduced machine-learned parametrizations of quantum Monte Carlo Ansätze rely on the efficiency of neural networks as universal function approximators to achieve state of the art accuracy on a variety of molecular systems. With interest in the field growing rapidly, there is a clear need for easy to use, modular, and extendable software libraries facilitating the development and adoption of this new class of methods. In this contribution, the DeepQMC program package is introduced, in an attempt to provide a common framework for future investigations by unifying many of the currently available deep-learning quantum Monte Carlo architectures. Furthermore, the manuscript provides a brief introduction to the methodology of variational quantum Monte Carlo in real space, highlights some technical challenges of optimizing neural network wave functions, and presents example black-box applications of the program package. We thereby intend to make this novel field accessible to a broader class of practitioners from both the quantum chemistry and the machine learning communities.

arXiv:2307.14123•The Journal of Chemical Physics•Sep 6, 2023•33 citations
Abstract An overview is presented of recent advances in applying variational, projection, and diffusion Monte Carlo methods (VMC, PMC, and DMC, respectively). The prospects for using the Monte Carlo method to calculate path integrals (PIMC) when modeling molecular systems are also considered. It is emphasized that modern machine learning effectively meets the requirements of parameterizing wave functions of the target space of solutions for a wide range of problems in quantum molecular modeling and functionals of the corresponding observables.
Quantum Monte Carlo methods are first-principle approaches that approximately solve the Schrödinger equation stochastically. As compared to traditional quantum chemistry methods, they offer important advantages such as the ability to handle a large variety of many-body wave functions, the favorable scaling with the number of particles, and the intrinsic parallelism of the algorithms which are particularly suitable to modern massively parallel computers. In this chapter, we focus on the two quantum Monte Carlo approaches most widely used for electronic structure problems, namely, the variational and diffusion Monte Carlo methods. We give particular attention to the recent progress in the techniques for the optimization of the wave function, a challenging and important step to achieve accurate results in both the ground and the excited state. We conclude with an overview of the current status of excited-state calculations for molecular systems, demonstrating the potential of quantum Monte Carlo methods in this field of applications.
Introduction In Chapters 1 to 4 we studied methods for solving the Schrödinger equation for many-electron systems. Many of the techniques described there carry over to other quantum many-particle systems, such as liquid helium, and the protons and neutrons in a nucleus. The techniques which we discussed there were, however, all of a mean-field type and therefore correlation effects could not be taken into account without introducing approximations. In this chapter, we consider more accurate techniques, which are similar to those studied in Chapter 10 and are based on using (pseudo-)random numbers – hence the name ‘Monte Carlo’ for these methods. In Chapter 10 we applied Monte Carlo techniques to classical many-particle systems; here we use these techniques for studying quantum problems involving many particles. In the next section we shall see how we can apply Monte Carlo techniques to the problem of calculating the quantum mechanical expectation value of the ground state energy. This is used in order to optimise this expectation value by adjusting a trial wave function in a variational type of approach, hence the name variational Monte Carlo (VMC). In the following section we use the similarity between the Schrödinger equation and the diffusion equation in order to calculate the properties of a collection of interacting quantum mechanical particles by simulating a classical particle diffusion process. The resulting method is called diffusion Monte Carlo (DMC).
KULAHLIOGLU, ADEM HALIL.Applications of the Fixed-Node Quantum Monte Carlo Method.(Under the direction of Lubos Mitas.)Quantum Monte Carlo (QMC) is a highly sophisticated quantum many-body method.Diffusion Monte Carlo (DMC), a projected QMC method, is a stochastic solution of the stationary Schrödinger's equation.It is, in principle, an exact method.However, in dealing with fermions, since trial wave functions meet the antisymmetric condition of the many-body fermionic systems, it inevitably encounters the fermion sign problem.One of the ways to circumvent the sign problem is by imposing the so-called fixed-node approximation.The fixed-node DMC (FN-DMC), a highly promising method, is emerging as the method
We propose a new method to calculate ground state position dependent observables in quantum many-body systems. The method, which we call the path-integral diffusion Monte Carlo (PI-DMC) method, is essentially a combination of path-integral Monte Carlo (PIMC) and diffusion Monte Carlo (DMC) methods. The distribution resulting from a DMC simulation is further propagated in imaginary time by PIMC sampling. Tests of the new method for simple cases such as the harmonic oscillator, a double well, and a set of ten coupled harmonic oscillators show that the results for several observables converge rapidly to the exact result.
In this article, machine-learning methods are used to solve quantum mechanics problems. The radial basis function network in a discrete basis is used as the variational wave function for the ground state of a quantum system. Variational Monte Carlo (VMC) calculations are carried out for some simple Hamiltonians. The results are in good agreement with theoretical values. The smallest eigenvalue of a Hermitian matrix can also be acquired using VMC calculations. Results are provided to demonstrate that machine-learning techniques are capable of solving quantum mechanical problems.
Computing accurate yet efficient approximations to the solutions of the electronic Schrödinger equation has been a paramount challenge of computational chemistry for decades. Quantum Monte Carlo methods are a promising avenue of development as their core algorithm exhibits a number of favorable properties: it is highly parallel and scales favorably with the considered system size, with an accuracy that is limited only by the choice of the wave function Ansatz. The recently introduced machine-learned parametrizations of quantum Monte Carlo Ansätze rely on the efficiency of neural networks as universal function approximators to achieve state of the art accuracy on a variety of molecular systems. With interest in the field growing rapidly, there is a clear need for easy to use, modular, and extendable software libraries facilitating the development and adoption of this new class of methods. In this contribution, the DeepQMC program package is introduced, in an attempt to provide a common framework for future investigations by unifying many of the currently available deep-learning quantum Monte Carlo architectures. Furthermore, the manuscript provides a brief introduction to the methodology of variational quantum Monte Carlo in real space, highlights some technical challenges of optimizing neural network wave functions, and presents example black-box applications of the program package. We thereby intend to make this novel field accessible to a broader class of practitioners from both the quantum chemistry and the machine learning communities.