Training models using forces computed by stochastic electronic structure methods

Ceperley, David M; Jensen, Scott; Yang, Yubo; Niu, Hongwei; Pierleoni, Carlo; Holzmann, Markus

doi:10.1088/2516-1075/ad2eb0

Cited by 4 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…35,36 Recently, the effect of the statistical noise on the resulting potentials has also been investigated. 37 Here, we show how QMC can yield forces as accurate as those computed with the "golden standard" of quantum chemistry, CCSD(T), over a large set of configurations of the fluxional ethanol molecule at room temperature. In particular, competitive accuracy can be obtained either in variational Monte Carlo (VMC) using multideterminant wave functions or in diffusion Monte Carlo (DMC) with the affordable variational-drift-diffusion approximation 28,29 molecular interactions, we also compare our results with DFT calculations treating dispersion interactions with the Tkatchenko−Scheffler (TS) 38 or the many-body dispersion (MBD) 39 approaches.…”

Section: Introductionmentioning

confidence: 93%

“…Quantum Monte Carlo (QMC) calculations can be instrumental in generating the reference data for accurate machine-learning potentials. Although QMC is computationally expensive, it provides highly accurate energies and forces, and scales favorably with system size also when forces are computed. − Calculating atomic forces in QMC has been an active field of research and different algorithms and approximations have been put forward for this purpose. − The use of QMC to construct machine-learning force fields is a relatively new field that has seen applications in the description of high-pressure hydrogen − and in molecular systems. , Recently, the effect of the statistical noise on the resulting potentials has also been investigated …”

Section: Introductionmentioning

confidence: 99%

“… 35 , 36 Recently, the effect of the statistical noise on the resulting potentials has also been investigated. 37 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accurate Quantum Monte Carlo Forces for Machine-Learned Force Fields: Ethanol as a Benchmark

Slootman,

Poltavsky,

Shinde

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Quantum Monte Carlo (QMC) is a powerful method to calculate accurate energies and forces for molecular systems. In this work, we demonstrate how we can obtain accurate QMC forces for the fluxional ethanol molecule at room temperature by using either multideterminant Jastrow-Slater wave functions in variational Monte Carlo or just a single determinant in diffusion Monte Carlo. The excellent performance of our protocols is assessed against high-level coupled cluster calculations on a diverse set of representative configurations of the system. Finally, we train machine-learning force fields on the QMC forces and compare them to models trained on coupled cluster reference data, showing that a force field based on the diffusion Monte Carlo forces with a single determinant can faithfully reproduce coupled cluster power spectra in molecular dynamics simulations.

show abstract

Section: Introductionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate Quantum Monte Carlo Forces for Machine-Learned Force Fields: Ethanol as a Benchmark

Slootman,

Poltavsky,

Shinde

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

show abstract

Force-Free Identification of Minimum-Energy Pathways and Transition States for Stochastic Electronic Structure Theories

Iyer,

Whelpley,

Tiihonen

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

The accurate mapping of potential energy surfaces (PESs) is crucial to our understanding of the numerous physical and chemical processes mediated by atomic rearrangements, such as conformational changes and chemical reactions, and the thermodynamic and kinetic feasibility of these processes. Stochastic electronic structure theories, e.g., Quantum Monte Carlo (QMC) methods, enable highly accurate total energy calculations that in principle can be used to construct the PES. However, their stochastic nature poses a challenge to the computation and use of forces and Hessians, which are typically required in algorithms for minimum-energy pathway (MEP) and transition state (TS) identification, such as the nudged elastic band (NEB) algorithm and its climbing image formulation. Here, we present strategies that utilize the surrogate Hessian line-search method, previously developed for QMC structural optimization, to efficiently identify MEP and TS structures without requiring force calculations at the level of the stochastic electronic structure theory. By modifying the surrogate Hessian algorithm to operate in path-orthogonal subspaces and at saddle points, we show that it is possible to identify MEPs and TSs by using a force-free QMC approach. We demonstrate these strategies via two examples, the inversion of the ammonia (NH 3 ) molecule and the nucleophilic substitution (S N 2) reaction F − + CH 3 F → FCH 3 + F − . We validate our results using Density Functional Theory (DFT)-and Coupled Cluster (CCSD, CCSD(T))-based NEB calculations. We then introduce a hybrid DFT-QMC approach to compute thermodynamic and kinetic quantities, free energy differences, rate constants, and equilibrium constants that incorporates stochastically optimized structures and their energies, and show that this scheme improves upon DFT accuracy. Our methods generalize straightforwardly to other systems and other high-accuracy theories that similarly face challenges computing energy gradients, paving the way for highly accurate PES mapping, transition state determination, and thermodynamic and kinetic calculations at significantly reduced computational expense.

show abstract

Stochastically accelerated perturbative triples correction in coupled cluster calculations

Damour,

Gallo,

Scemama

2024

The Journal of Chemical Physics

View full text Add to dashboard Cite

We introduce a novel algorithm that leverages stochastic sampling techniques to compute the perturbative triples correction in the coupled-cluster framework. By combining elements of randomness and determinism, our algorithm achieves a favorable balance between accuracy and computational cost. The main advantage of this algorithm is that it allows for the calculation to be stopped at any time, providing an unbiased estimate, with a statistical error that goes to zero as the exact calculation is approached. We provide evidence that our semi-stochastic algorithm achieves substantial computational savings compared to traditional deterministic methods. Specifically, we demonstrate that a precision of 0.5 millihartree can be attained with only 10% of the computational effort required by the full calculation. This work opens up new avenues for efficient and accurate computations, enabling investigations of complex molecular systems that were previously computationally prohibitive.

show abstract

Training models using forces computed by stochastic electronic structure methods

Cited by 4 publications

References 53 publications

Accurate Quantum Monte Carlo Forces for Machine-Learned Force Fields: Ethanol as a Benchmark

Accurate Quantum Monte Carlo Forces for Machine-Learned Force Fields: Ethanol as a Benchmark

Force-Free Identification of Minimum-Energy Pathways and Transition States for Stochastic Electronic Structure Theories

Stochastically accelerated perturbative triples correction in coupled cluster calculations

Contact Info

Product

Resources

About