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

arXiv:2505.00233 · ACM Transactions on AI for Science

Explorative Curriculum Learning for Strongly Correlated Electron Systems

Kimihiro Yamazaki, Takuya Konishi, Yoshinobu Kawahara

Published Mar 25, 2026• 0 citations
arXivHTMLPDF

Abstract

Recent advances in neural network quantum states (NQS) have enabled high-accuracy predictions for complex quantum many-body systems such as strongly correlated electron systems. However, the computational cost remains prohibitive, making exploration of the diverse parameters of interaction strengths and other physical parameters inefficient. While transfer learning has been proposed to mitigate this challenge, achieving generalization to large-scale systems and diverse parameter regimes remains difficult. To address this limitation, we propose a novel curriculum learning framework based on transfer learning for NQS. This facilitates efficient and stable exploration across a vast parameter space of quantum many-body systems. In addition, by interpreting NQS transfer learning through a perturbative lens, we demonstrate how prior physical knowledge can be flexibly incorporated into the curriculum learning process. We also propose Pairing-Net, an architecture based on the neural pair-product state to practically implement this strategy for strongly correlated electron systems, and empirically verify its effectiveness. Our results show that our physics-informed approach leads to a significant improvement in computational efficiency and optimization stability compared to conventional methods.

DOI
10.1145/3800609

Related papers

New approaches to strongly correlated electron systems

Hannah Lange

Strongly correlated materials exhibit complex emergent phenomena -- such as unconventional high-temperature superconductivity -- that cannot be explained within a single or weakly-interacting particle description, making understanding their physics a central challenge in condensed matter physics. This thesis develops and applies novel approaches to strongly correlated electron systems, focusing on neural quantum states (NQS) and quantum simulation with cold atoms in optical lattices or Rydberg tweezer arrays. A key contribution of this work is the advancement of neural-network-based representations of quantum many-body states. By employing state-of-the-art network architectures like Transformers and combining them with physical constructions such as determinants, Pfaffians and Gutzwiller-projection, NQS are extended to simulate large two-dimensional fermionic single- and multi-band systems with high accuracy and beyond the capabilities of conventional methods. In addition, the thesis explores how quantum simulators based on ultracold atoms in optical lattices can be leveraged to study models directly relevant to strongly correlated materials -- e.g. the multi-band model of cuprate superconductors -- as well as proposes strategies to probe superconductivity in this setting. Furthermore, hybrid approaches that combine NQS with data from quantum simulators are developed. This synergy allows for improved optimization and direct comparison between theory and experiment. These methodological developments are applied to investigate two fundamental questions in high-temperature superconductivity: On the one hand, the work proposes a microscopic mechanism based on Feshbach resonances and tests this hypothesis extensively in a model system relevant to cuprates, nickelates and heavy fermion materials. On the other hand, it develops systematic approaches to derive effective low-energy models from more complex systems like multi-band models or electron-phonon coupled systems, shining light on the timely question which single-band models capture the physics of high-temperature superconductors like cuprate or nickelate materials. Overall, the thesis demonstrates how combining machine learning and quantum simulation provides powerful tools for understanding strongly correlated quantum matter.

•Jul 24, 2026•0 citations

Fine-tuning neural network quantum states

Riccardo Rende, Sebastian Goldt, Federico Becca +1 more

Recent progress in the design and optimization of neural-network quantum states (NQSs) has made them an effective method to investigate ground-state properties of quantum many-body systems. In contrast to the standard approach of training a separate NQS from scratch at every point of the phase diagram, we demonstrate that the optimization of a NQS at a highly expressive point of the phase diagram (i.e., close to a phase transition) yields features that can be reused to accurately describe a wide region across the transition. We demonstrate the feasibility of our approach on different systems in one and two dimensions by initially pretraining a NQS at a given point of the phase diagram, followed by fine-tuning only the output layer for all other points. Notably, the computational cost of the fine-tuning step is very low compared to the pretraining stage. We argue that the reduced cost of this paradigm has significant potential to advance the exploration of strongly correlated systems using NQS, mirroring the success of fine-tuning in machine learning and natural language processing. Published by the American Physical Society 2024

arXiv:2403.07795•Physical Review Research•Dec 16, 2024•10 citations

Transfer learning for scalability of neural-network quantum states

Remmy A. M. Zen, Long D. H. My, Ryan Tan +5 more

Neural-network quantum states have shown great potential for the study of many-body quantum systems. In statistical machine learning, transfer learning designates protocols reusing features of a machine learning model trained for a problem to solve a possibly related but different problem. We propose to evaluate the potential of transfer learning to improve the scalability of neural-network quantum states. We devise and present physics-inspired transfer learning protocols, reusing the features of neural-network quantum states learned for the computation of the ground state of a small system for systems of larger sizes. We implement different protocols for restricted Boltzmann machines on general-purpose graphics processing units. This implementation alone yields a speedup over existing implementations on multicore and distributed central processing units in comparable settings. We empirically and comparatively evaluate the efficiency (time) and effectiveness (accuracy) of different transfer learning protocols as we scale the system size in different models and different quantum phases. Namely, we consider both the transverse field Ising and Heisenberg XXZ models in one dimension, as well as in two dimensions for the latter, with system sizes up to 128 and 8×8 spins. We empirically demonstrate that some of the transfer learning protocols that we have devised can be far more effective and efficient than starting from neural-network quantum states with randomly initialized parameters.

arXiv:1908.09883•Physical review. E•May 5, 2020•50 citations

Neural-network quantum states for ultra-cold Fermi gases

Jane Kim, Gabriel Pescia, Bryce Fore +5 more

Ultra-cold Fermi gases display diverse quantum mechanical properties, including the transition from a fermionic superfluid BCS state to a bosonic superfluid BEC state, which can be probed experimentally with high precision. However, the theoretical description of these properties is challenging due to the onset of strong pairing correlations and the non-perturbative nature of the interaction among the constituent particles. This work introduces a novel Pfaffian-Jastrow neural-network quantum state that includes backflow transformation based on message-passing architecture to efficiently encode pairing, and other quantum mechanical correlations. Our approach offers substantial improvements over comparable ansätze constructed within the Slater-Jastrow framework and outperforms state-of-the-art diffusion Monte Carlo methods, as indicated by our lower ground-state energies. We observe the emergence of strong pairing correlations through the opposite-spin pair distribution functions. Moreover, we demonstrate that transfer learning stabilizes and accelerates the training of the neural-network wave function, enabling the exploration of the BCS-BEC crossover region near unitarity. Our findings suggest that neural-network quantum states provide a promising strategy for studying ultra-cold Fermi gases.

arXiv:2305.08831•May 15, 2023•1 citation

Structure and dynamics of electron-phonon coupled systems using neural quantum states

Ankit Mahajan, Paul J. Robinson, Joonho Lee +1 more

In this work, we use neural quantum states (NQS) to describe the high-dimensional wave functions of electron-phonon coupled systems. We demonstrate that NQS can accurately and systematically learn the underlying physics of such problems through a variational Monte Carlo optimization of the energy with minimal incorporation of physical information, even in highly challenging cases. We assess the ability of our approach across various lattice model examples featuring different types of couplings. The flexibility of our NQS formulation is demonstrated via application to ab initio models parametrized by density functional perturbation theory consisting of electron or hole bands coupled linearly to dispersive phonons. We compute accurate real-frequency spectral properties of electron-phonon via a response formalism based on NQS. Our work establishes a general framework for exploring diverse ground-state and dynamical phenomena arising in electron-phonon systems, including the nonperturbative interplay of correlated electronic and electron-phonon effects in systems ranging from simple lattice models to realistic models of materials parametrized by ab initio calculations.

arXiv:2405.08701•Physical review. B./Physical review. B•Nov 18, 2025•2 citations

First-principles Deep Learning for Quantum Many-body Physics

Khachatur G. Nazaryan

This thesis investigates emergent phenomena in strongly correlated quantum matter, with a central focus on developing first-principles deep learning methods for quantum many-body systems. A common theme throughout this work is the search for microscopic mechanisms that generate unexpected collective behavior, together with computational frameworks capable of describing such behavior in regimes where conventional approaches become inadequate. The first part of the thesis studies a doped Mott insulator in a magnetic field and uncovers a new superconducting state, which we call \emph{magnonic superconductivity}. In this state, magnons mediate pairing, and the superconducting order is carried by composite objects binding electron pairs to spin excitations. This mechanism gives rise to a partially spin-polarized superconducting phase beyond the conventional paradigm of electron pairing and further suggests the possibility of higher-charge bound states, including charge-$6e$ superconductivity. The main thrust of the thesis is the use of deep neural networks as variational, first-principles representations of many-body wave functions. In contrast to the usual data-driven role of machine learning, the neural-network ans\"atze developed here do not learn from labeled datasets; instead, they are optimized directly from the microscopic Hamiltonian through variational Monte Carlo. Within this framework, we first develop self-attention-based neural-network wave functions for correlated electrons in solids and show that they accurately describe moir\'e systems with minimal human bias, capture interaction-driven phase transitions, and exhibit favorable scaling of representational complexity with system size. We then introduce a general physics-informed initialization strategy that reconstructs complex many-body wave functions from probability density and probability current. This approach enables highly accurate pretraining of neural wave functions, achieves near-exact overlaps for topological and paired quantum states, and allows efficient simulations of fractional quantum Hall systems with realistic interactions at unprecedented sizes. Finally, we introduce QERNEL, an efficient foundational neural variational ansatz designed to learn a family of many-body ground states within a single conditional model. By combining efficient context conditioning with modern permutation-equivariant building blocks, QERNEL achieves substantially improved expressivity at low computational cost. Applied to interacting electrons in semiconductor moir\'e heterobilayers, it captures distinct many-body phases and resolves the sharp phase transition between them in systems as large as 150 electrons. These results show that context-aware neural wave functions can move beyond Hamiltonian-by-Hamiltonian solution toward genuinely foundational models of quantum matter. Taken together, the results of this thesis show that first-principles deep learning can serve not merely as a numerical tool, but as a general framework for quantum many-body physics: one that bridges microscopic Hamiltonians, expressive wave-function ansätze, and scalable computation, while opening new paths to the discovery and characterization of strongly correlated quantum matter.

•May 1, 2026•0 citations
Recent advances in neural network quantum states (NQS) have enabled high-accuracy predictions for complex quantum many-body systems such as strongly correlated electron systems. However, the computational cost remains prohibitive, making exploration of the diverse parameters of interaction strengths and other physical parameters inefficient. While transfer learning has been proposed to mitigate this challenge, achieving generalization to large-scale systems and diverse parameter regimes remains difficult. To address this limitation, we propose a novel curriculum learning framework based on transfer learning for NQS. This facilitates efficient and stable exploration across a vast parameter space of quantum many-body systems. In addition, by interpreting NQS transfer learning through a perturbative lens, we demonstrate how prior physical knowledge can be flexibly incorporated into the curriculum learning process. We also propose Pairing-Net, an architecture based on the neural pair-product state to practically implement this strategy for strongly correlated electron systems, and empirically verify its effectiveness. Our results show that our physics-informed approach leads to a significant improvement in computational efficiency and optimization stability compared to conventional methods.
Strongly correlated materials exhibit complex emergent phenomena -- such as unconventional high-temperature superconductivity -- that cannot be explained within a single or weakly-interacting particle description, making understanding their physics a central challenge in condensed matter physics. This thesis develops and applies novel approaches to strongly correlated electron systems, focusing on neural quantum states (NQS) and quantum simulation with cold atoms in optical lattices or Rydberg tweezer arrays. A key contribution of this work is the advancement of neural-network-based representations of quantum many-body states. By employing state-of-the-art network architectures like Transformers and combining them with physical constructions such as determinants, Pfaffians and Gutzwiller-projection, NQS are extended to simulate large two-dimensional fermionic single- and multi-band systems with high accuracy and beyond the capabilities of conventional methods. In addition, the thesis explores how quantum simulators based on ultracold atoms in optical lattices can be leveraged to study models directly relevant to strongly correlated materials -- e.g. the multi-band model of cuprate superconductors -- as well as proposes strategies to probe superconductivity in this setting. Furthermore, hybrid approaches that combine NQS with data from quantum simulators are developed. This synergy allows for improved optimization and direct comparison between theory and experiment. These methodological developments are applied to investigate two fundamental questions in high-temperature superconductivity: On the one hand, the work proposes a microscopic mechanism based on Feshbach resonances and tests this hypothesis extensively in a model system relevant to cuprates, nickelates and heavy fermion materials. On the other hand, it develops systematic approaches to derive effective low-energy models from more complex systems like multi-band models or electron-phonon coupled systems, shining light on the timely question which single-band models capture the physics of high-temperature superconductors like cuprate or nickelate materials. Overall, the thesis demonstrates how combining machine learning and quantum simulation provides powerful tools for understanding strongly correlated quantum matter.
Recent progress in the design and optimization of neural-network quantum states (NQSs) has made them an effective method to investigate ground-state properties of quantum many-body systems. In contrast to the standard approach of training a separate NQS from scratch at every point of the phase diagram, we demonstrate that the optimization of a NQS at a highly expressive point of the phase diagram (i.e., close to a phase transition) yields features that can be reused to accurately describe a wide region across the transition. We demonstrate the feasibility of our approach on different systems in one and two dimensions by initially pretraining a NQS at a given point of the phase diagram, followed by fine-tuning only the output layer for all other points. Notably, the computational cost of the fine-tuning step is very low compared to the pretraining stage. We argue that the reduced cost of this paradigm has significant potential to advance the exploration of strongly correlated systems using NQS, mirroring the success of fine-tuning in machine learning and natural language processing. Published by the American Physical Society 2024
Neural-network quantum states have shown great potential for the study of many-body quantum systems. In statistical machine learning, transfer learning designates protocols reusing features of a machine learning model trained for a problem to solve a possibly related but different problem. We propose to evaluate the potential of transfer learning to improve the scalability of neural-network quantum states. We devise and present physics-inspired transfer learning protocols, reusing the features of neural-network quantum states learned for the computation of the ground state of a small system for systems of larger sizes. We implement different protocols for restricted Boltzmann machines on general-purpose graphics processing units. This implementation alone yields a speedup over existing implementations on multicore and distributed central processing units in comparable settings. We empirically and comparatively evaluate the efficiency (time) and effectiveness (accuracy) of different transfer learning protocols as we scale the system size in different models and different quantum phases. Namely, we consider both the transverse field Ising and Heisenberg XXZ models in one dimension, as well as in two dimensions for the latter, with system sizes up to 128 and 8×8 spins. We empirically demonstrate that some of the transfer learning protocols that we have devised can be far more effective and efficient than starting from neural-network quantum states with randomly initialized parameters.
Ultra-cold Fermi gases display diverse quantum mechanical properties, including the transition from a fermionic superfluid BCS state to a bosonic superfluid BEC state, which can be probed experimentally with high precision. However, the theoretical description of these properties is challenging due to the onset of strong pairing correlations and the non-perturbative nature of the interaction among the constituent particles. This work introduces a novel Pfaffian-Jastrow neural-network quantum state that includes backflow transformation based on message-passing architecture to efficiently encode pairing, and other quantum mechanical correlations. Our approach offers substantial improvements over comparable ansätze constructed within the Slater-Jastrow framework and outperforms state-of-the-art diffusion Monte Carlo methods, as indicated by our lower ground-state energies. We observe the emergence of strong pairing correlations through the opposite-spin pair distribution functions. Moreover, we demonstrate that transfer learning stabilizes and accelerates the training of the neural-network wave function, enabling the exploration of the BCS-BEC crossover region near unitarity. Our findings suggest that neural-network quantum states provide a promising strategy for studying ultra-cold Fermi gases.
In this work, we use neural quantum states (NQS) to describe the high-dimensional wave functions of electron-phonon coupled systems. We demonstrate that NQS can accurately and systematically learn the underlying physics of such problems through a variational Monte Carlo optimization of the energy with minimal incorporation of physical information, even in highly challenging cases. We assess the ability of our approach across various lattice model examples featuring different types of couplings. The flexibility of our NQS formulation is demonstrated via application to ab initio models parametrized by density functional perturbation theory consisting of electron or hole bands coupled linearly to dispersive phonons. We compute accurate real-frequency spectral properties of electron-phonon via a response formalism based on NQS. Our work establishes a general framework for exploring diverse ground-state and dynamical phenomena arising in electron-phonon systems, including the nonperturbative interplay of correlated electronic and electron-phonon effects in systems ranging from simple lattice models to realistic models of materials parametrized by ab initio calculations.
This thesis investigates emergent phenomena in strongly correlated quantum matter, with a central focus on developing first-principles deep learning methods for quantum many-body systems. A common theme throughout this work is the search for microscopic mechanisms that generate unexpected collective behavior, together with computational frameworks capable of describing such behavior in regimes where conventional approaches become inadequate. The first part of the thesis studies a doped Mott insulator in a magnetic field and uncovers a new superconducting state, which we call \emph{magnonic superconductivity}. In this state, magnons mediate pairing, and the superconducting order is carried by composite objects binding electron pairs to spin excitations. This mechanism gives rise to a partially spin-polarized superconducting phase beyond the conventional paradigm of electron pairing and further suggests the possibility of higher-charge bound states, including charge-6e6e6e superconductivity. The main thrust of the thesis is the use of deep neural networks as variational, first-principles representations of many-body wave functions. In contrast to the usual data-driven role of machine learning, the neural-network ans\"atze developed here do not learn from labeled datasets; instead, they are optimized directly from the microscopic Hamiltonian through variational Monte Carlo. Within this framework, we first develop self-attention-based neural-network wave functions for correlated electrons in solids and show that they accurately describe moir\'e systems with minimal human bias, capture interaction-driven phase transitions, and exhibit favorable scaling of representational complexity with system size. We then introduce a general physics-informed initialization strategy that reconstructs complex many-body wave functions from probability density and probability current. This approach enables highly accurate pretraining of neural wave functions, achieves near-exact overlaps for topological and paired quantum states, and allows efficient simulations of fractional quantum Hall systems with realistic interactions at unprecedented sizes. Finally, we introduce QERNEL, an efficient foundational neural variational ansatz designed to learn a family of many-body ground states within a single conditional model. By combining efficient context conditioning with modern permutation-equivariant building blocks, QERNEL achieves substantially improved expressivity at low computational cost. Applied to interacting electrons in semiconductor moir\'e heterobilayers, it captures distinct many-body phases and resolves the sharp phase transition between them in systems as large as 150 electrons. These results show that context-aware neural wave functions can move beyond Hamiltonian-by-Hamiltonian solution toward genuinely foundational models of quantum matter. Taken together, the results of this thesis show that first-principles deep learning can serve not merely as a numerical tool, but as a general framework for quantum many-body physics: one that bridges microscopic Hamiltonians, expressive wave-function ansätze, and scalable computation, while opening new paths to the discovery and characterization of strongly correlated quantum matter.