000165615 001__ 165615
000165615 005__ 20260112132217.0
000165615 0247_ $$2doi$$a10.1088/2632-2153/ae29bb
000165615 0248_ $$2sideral$$a147320
000165615 037__ $$aART-2025-147320
000165615 041__ $$aeng
000165615 100__ $$aGallego, Manuel$$uUniversidad de Zaragoza
000165615 245__ $$aAccelerating quantum Monte Carlo calculations with set-equivariant architectures and transfer learning
000165615 260__ $$c2025
000165615 5060_ $$aAccess copy available to the general public$$fUnrestricted
000165615 5203_ $$aMachine-learning ansätze have greatly expanded the accuracy and reach of variational quantum Monte Carlo (QMC) calculations, in particular when exploring the manifold quantum phenomena exhibited by spin systems. However, the scalability of QMC is still compromised by several other bottlenecks, and specifically those related to the actual evaluation of observables based on random deviates that lies at the core of the approach. Here we show how the set-transformer architecture can be used to dramatically accelerate or even bypass that step, especially for time-consuming operators such as powers of the magnetization. We illustrate the procedure with a range of examples structured around quantum spin systems with long-range interactions, and comprising both regressions (to predict observables) and classifications (to detect phase transitions). Moreover, we show how transfer learning can be leveraged to reduce the training cost by reusing knowledge from different systems and smaller system sizes.
000165615 536__ $$9info:eu-repo/grantAgreement/ES/MICIU/CEX2023-001286-S$$9info:eu-repo/grantAgreement/ES/MICIU/PRTR-C17.I1$$9info:eu-repo/grantAgreement/ES/MICIU/AEI/10.13039/501100011033
000165615 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000165615 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000165615 700__ $$aRoca-Jerat, Sebastián
000165615 700__ $$0(orcid)0000-0003-4478-1948$$aZueco, David
000165615 700__ $$0(orcid)0000-0003-0971-1098$$aCarrete, Jesús
000165615 7102_ $$12004$$2405$$aUniversidad de Zaragoza$$bDpto. Física Teórica$$cÁrea Física Teórica
000165615 773__ $$g6, 4 (2025), 045070 [13 pp.]$$tMachine Learning: Science and Technology$$x2632-2153
000165615 8564_ $$s1104684$$uhttps://zaguan.unizar.es/record/165615/files/texto_completo.pdf$$yVersión publicada
000165615 8564_ $$s751369$$uhttps://zaguan.unizar.es/record/165615/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000165615 909CO $$ooai:zaguan.unizar.es:165615$$particulos$$pdriver
000165615 951__ $$a2026-01-12-11:11:14
000165615 980__ $$aARTICLE