Kolmogorov-Arnold wavefunctions

Bedaque, Paulo F.; Cigliano, Jacob; Kumar, Hersh; Paul, Srijit; Rajawat, Suryansh

doi:10.1103/zj4l-h6nv

Kolmogorov-Arnold wavefunctions

Journal Article · Mon Nov 24 00:00:00 EST 2025 · Physical Review. C

DOI:https://doi.org/10.1103/zj4l-h6nv· OSTI ID:3007459

^[1]; ^[1]; ^[1]; ^[1]; Rajawat, Suryansh ^[1]

Univ. of Maryland, College Park, MD (United States)

Here, this work investigates Kolmogorov-Arnold network-based (KAN) wave-function Ansätz as viable representations for quantum Monte Carlo simulations. Through systematic analysis of one-dimensional model systems, we evaluate their computational efficiency and representational power against established methods. Our numerical experiments suggest some efficient training methods and we explore how the computational cost scales with desired precision, particle number, and system parameters. Roughly speaking, KANs seem to be 10 times cheaper computationally than other neural-network-based Ansätz. We also introduce a novel approach for handling strong short-range potentials—a persistent challenge for many numerical techniques—which generalizes efficiently to higher-dimensional, physically relevant systems with short-ranged strong potentials common in atomic and nuclear physics.

View Accepted Manuscript (DOE)

Research Organization:: Univ. of Maryland, College Park, MD (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Nuclear Physics (NP)

Grant/Contract Number:: FG02-93ER40762

Other Award/Contract Number:: KA2401045

OSTI ID:: 3007459

Journal Information:: Physical Review. C, Journal Name: Physical Review. C Journal Issue: 5 Vol. 112; ISSN 2469-9985; ISSN 2469-9993

Publisher:: American Physical Society (APS)Copyright Statement

Country of Publication:: United States

Language:: English

References (31)

On the eigenfunctions of many-particle systems in quantum mechanics Kato, Tosio Communications on Pure and Applied Mathematics, Vol. 10, Issue 2 https://doi.org/10.1002/cpa.3160100201	journal	January 1957
A geometric wave function for a few interacting bosons in a harmonic trap Wilson, B.; Foerster, A.; Kuhn, C. C. N. Physics Letters A, Vol. 378, Issue 16-17 https://doi.org/10.1016/j.physleta.2014.02.009	journal	March 2014
Machine learning the deuteron Keeble, J. W. T.; Rios, A. Physics Letters B, Vol. 809 https://doi.org/10.1016/j.physletb.2020.135743	journal	October 2020
Two Cold Atoms in a Harmonic Trap Busch, Thomas; Englert, Berthold-Georg; Rzażewski, Kazimierz Foundations of Physics, Vol. 28, Issue 4, p. 549-559 https://doi.org/10.1023/A:1018705520999	journal	April 1998
Ab-initio variational wave functions for the time-dependent many-electron Schrödinger equation Nys, Jannes; Pescia, Gabriel; Sinibaldi, Alessandro Nature Communications, Vol. 15, Issue 1 https://doi.org/10.1038/s41467-024-53672-w	journal	October 2024
Deep-neural-network solution of the electronic Schrödinger equation Hermann, Jan; Schätzle, Zeno; Noé, Frank Nature Chemistry, Vol. 12, Issue 10 https://doi.org/10.1038/s41557-020-0544-y	journal	September 2020
Pair-correlation ansatz for the ground state of interacting bosons in an arbitrary one-dimensional potential Kościk, Przemysław; Kuroś, Arkadiusz; Pieprzycki, Adam Scientific Reports, Vol. 11, Issue 1 https://doi.org/10.1038/s41598-021-92556-7	journal	June 2021
Neural-network quantum states for ultra-cold Fermi gases Kim, Jane; Pescia, Gabriel; Fore, Bryce Communications Physics, Vol. 7, 148 https://doi.org/10.1038/s42005-024-01613-w	journal	May 2024
Relationship between Systems of Impenetrable Bosons and Fermions in One Dimension Girardeau, M. Journal of Mathematical Physics, Vol. 1, Issue 6 https://doi.org/10.1063/1.1703687	journal	November 1960
Quantum Monte Carlo study of quasi-one-dimensional Bose gases Astrakharchik, G. E.; Blume, D.; Giorgini, S. Journal of Physics B: Atomic, Molecular and Optical Physics, Vol. 37, Issue 7 https://doi.org/10.1088/0953-4075/37/7/066	journal	March 2004
Three interacting atoms in a one-dimensional trap: a benchmark system for computational approaches D’Amico, Pino; Rontani, Massimo Journal of Physics B: Atomic, Molecular and Optical Physics, Vol. 47, Issue 6 https://doi.org/10.1088/0953-4075/47/6/065303	journal	February 2014
Monte Carlo Calculations of the Ground State of Three- and Four-Body Nuclei Kalos, M. H. Physical Review, Vol. 128, Issue 4 https://doi.org/10.1103/PhysRev.128.1791	journal	November 1962
The Complete Equation of State of One, Two and Three-Dimensional Gases of Hard Elastic Spheres Tonks, Lewi Physical Review, Vol. 50, Issue 10 https://doi.org/10.1103/PhysRev.50.955	journal	November 1936
Machine learning one-dimensional spinless trapped fermionic systems with neural-network quantum states Keeble, J. W. T.; Drissi, M.; Rojo-Francàs, A. Physical Review A, Vol. 108, Issue 6 https://doi.org/10.1103/PhysRevA.108.063320	journal	December 2023
Symmetries of three harmonically trapped particles in one dimension Harshman, N. L. Physical Review A, Vol. 86, Issue 5 https://doi.org/10.1103/PhysRevA.86.052122	journal	November 2012
Deep-neural-network approach to solving the ab initio nuclear structure problem Yang, Y. L.; Zhao, P. W. Physical Review C, Vol. 107, Issue 3 https://doi.org/10.1103/PhysRevC.107.034320	journal	March 2023
Neural network solutions of bosonic quantum systems in one dimension Bedaque, Paulo F.; Kumar, Hersh; Sheng, Andy Physical Review C, Vol. 109, Issue 3 https://doi.org/10.1103/PhysRevC.109.034004	journal	March 2024
Leveraging neural control variates for enhanced precision in lattice field theory Bedaque, Paulo F.; Oh, Hyunwoo Physical Review D, Vol. 109, Issue 9 https://doi.org/10.1103/PhysRevD.109.094519	journal	May 2024
Control variates for lattice field theory Bhattacharya, Tanmoy; Lawrence, Scott; Yoo, Jun-Sik Physical Review D, Vol. 109, Issue 3 https://doi.org/10.1103/PhysRevD.109.L031505	journal	February 2024
Solving the nuclear pairing model with neural network quantum states Rigo, Mauro; Hall, Benjamin; Hjorth-Jensen, Morten Physical Review E, Vol. 107, Issue 2 https://doi.org/10.1103/PhysRevE.107.025310	journal	February 2023
Construction of Analytical Many-Body Wave Functions for Correlated Bosons in a Harmonic Trap Brouzos, Ioannis; Schmelcher, Peter Physical Review Letters, Vol. 108, Issue 4 https://doi.org/10.1103/PhysRevLett.108.045301	journal	January 2012
Exactly Solvable System of One-Dimensional Trapped Bosons with Short- and Long-Range Interactions Beau, M.; Pittman, S. M.; Astrakharchik, G. E. Physical Review Letters, Vol. 125, Issue 22 https://doi.org/10.1103/PhysRevLett.125.220602	journal	November 2020
Variational Monte Carlo Calculations of A ≤ 4 Nuclei with an Artificial Neural-Network Correlator Ansatz Adams, Corey; Carleo, Giuseppe; Lovato, Alessandro Physical Review Letters, Vol. 127, Issue 2 https://doi.org/10.1103/PhysRevLett.127.022502	journal	July 2021
Distilling the Essential Elements of Nuclear Binding via Neural-Network Quantum States Gnech, Alex; Fore, Bryce; Tropiano, Anthony J. Physical Review Letters, Vol. 133, Issue 14 https://doi.org/10.1103/PhysRevLett.133.142501	journal	October 2024
Quasi-One-Dimensional Bose Gases with a Large Scattering Length Astrakharchik, G. E.; Blume, D.; Giorgini, S. Physical Review Letters, Vol. 92, Issue 3 https://doi.org/10.1103/PhysRevLett.92.030402	journal	January 2004
Ab initio solution of the many-electron Schrödinger equation with deep neural networks Pfau, David; Spencer, James S.; Matthews, Alexander G. D. G. Physical Review Research, Vol. 2, Issue 3 https://doi.org/10.1103/PhysRevResearch.2.033429	journal	September 2020
Hidden-nucleons neural-network quantum states for the nuclear many-body problem Lovato, Alessandro; Adams, Corey; Carleo, Giuseppe Physical Review Research, Vol. 4, Issue 4 https://doi.org/10.1103/PhysRevResearch.4.043178	journal	December 2022
Solving the quantum many-body problem with artificial neural networks Carleo, Giuseppe; Troyer, Matthias Science, Vol. 355, Issue 6325 https://doi.org/10.1126/science.aag2302	journal	February 2017
Representation Properties of Networks: Kolmogorov's Theorem Is Irrelevant Girosi, Federico; Poggio, Tomaso Neural Computation, Vol. 1, Issue 4 https://doi.org/10.1162/neco.1989.1.4.465	journal	December 1989
Kolmogorov's Theorem Is Relevant Kůrková, Věra Neural Computation, Vol. 3, Issue 4 https://doi.org/10.1162/neco.1991.3.4.617	journal	December 1991
Method to Solve Quantum Few-Body Problems with Artificial Neural Networks Saito, Hiroki Journal of the Physical Society of Japan, Vol. 87, Issue 7 https://doi.org/10.7566/JPSJ.87.074002	journal	July 2018

Similar Records

SPIKANs: separable physics-informed Kolmogorov–Arnold networks

Journal Article · Sun Sep 21 20:00:00 EDT 2025 · Machine Learning: Science and Technology · OSTI ID:3015493

Baseflow Identification via Explainable AI With Kolmogorov‐Arnold Networks

Journal Article · Sun Nov 30 19:00:00 EST 2025 · Journal of Geophysical Research: Machine Learning and Computation · OSTI ID:3004776

SineKAN: Kolmogorov-Arnold Networks using sinusoidal activation functions

Journal Article · Tue Jan 14 19:00:00 EST 2025 · Frontiers in Artificial Intelligence · OSTI ID:2500918

Related Subjects

1-dimensional systems
approximation methods for many-body systems
artificial neural networks
bosons
few-body systems
machine learning
quantum many-body systems

Kolmogorov-Arnold wavefunctions

Citation Formats

References (31)

Similar Records

Related Subjects