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:2610.10697

The surprising simplicity of forecasting quantum chaotic many-body dynamics

Francesco Perciavalle, Agostino Gallo, Francesco Plastina, Gianluigi Greco, Nicola Lo Gullo, Carlo Adornetto

quant-phcond-mat.stat-mechcs.LGSubmitted Oct 7, 2026• Announced Oct 9, 2026• 0 citations• Revised Oct 20, 2026 (v2)
v1 · Oct 7, 2026v2 · Oct 20, 2026
arXivHTMLPDF

Abstract

Accurately simulating chaotic quantum many-body dynamics remains a major computational challenge for classical methods, due to the rapid buildup and spatial spreading of entanglement during the evolution. This raises the question of whether machine learning can provide an effective alternative for predicting quantum dynamics. We address this question by formulating quantum dynamics as a time-series forecasting problem, using a few-qubit PXP chain, realizable with Rydberg-atom arrays, as a benchmark. By varying the initial state, the system spans dynamical regimes ranging from ergodic behavior to quantum many-body scarring, providing a controlled setting for testing forecasting models across qualitatively different dynamics. We compare two contrasting architectures: an expressive nonlinear Transformer and DLinear, a simple linear forecasting model. The Transformer accurately predicts dynamics in the more ergodic regime, but its performance progressively deteriorates as the initial state approaches the scarred limit. In contrast, DLinear remains accurate across the entire family of initial states, with its main deviations consisting of small high-frequency oscillations that have little effect on the overall prediction error. Remarkably, these results show that observables generated by complex quantum many-body dynamics can be forecast with high accuracy through a simple linear mapping from past to future observations. This reveals that the complexity of the underlying quantum evolution need not translate into an equally complex forecasting problem.

AI Summary

The paper asks whether forecasting observables of chaotic quantum many-body dynamics requires an expressive nonlinear model. It compares DLinear, a linear time-series forecasting architecture, with an autoregressive Transformer on a PXP chain exhibiting both thermalizing and quantum-scarred dynamics. The benchmark uses exact evolution of an $L=10$ open chain for 500 initial states sampled from a two-parameter family interpolating between polarized and Néel configurations, including entangled superpositions. Each trajectory contains 55 features: local magnetizations and all connected two-site $zz$ correlations. Models receive 500 samples covering $t\in[0,10)$ and predict 300 samples over $t\in[10,16)$, with $\Delta t=0.02$. There are 400 training/validation trajectories and 100 held-out test trajectories. Both models use a loss penalizing value errors and discrepancies in temporal increments and directions; DLinear predicts the entire horizon directly, whereas the Transformer generates it recursively. DLinear yields low, comparatively uniform mean absolute errors across the initial-state family. Its raw directional accuracy is approximately $50\%$, attributed to small high-frequency prediction artifacts; smoothing raises it above $90\%$ across much of parameter space. Transformer errors increase toward the scarred regime, with local absolute errors approaching $0.7$ in the selected worst-case trajectory. Its error grows more strongly over the forecast horizon. The stated limitations are the single finite chain, restricted initial-state family, selected observables, and fixed forecasting horizon. Generalization to other Hamiltonians, larger systems, circuits, and open-system dynamics remains unestablished.

Some signs of AI-generated textSmall numerics onlyMissing comparisonIncrementalOverclaims

Error found: Because DLinear uses direct multi-step prediction and the Transformer uses teacher-forced autoregressive prediction, their comparison does not isolate linear versus nonlinear expressiveness as the reason for the performance difference. The paper gives incompatible Transformer protocols—sliding-window next-step forecasting and target-sequence encoder–decoder forecasting—leaving the implementation underlying the reported comparison ambiguous.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
Francesco Perciavalle and Agostino Gallo contributed equally to this work. 11 pages, 5 figures

Related papers

Quantum vs. classical: a comprehensive benchmark study for predicting time series with variational quantum machine learning

Tobias Fellner, David A. Kreplin, Samuel Tovey +1 more

Abstract Variational quantum machine learning algorithms have been proposed as promising tools for time series prediction, with the potential to handle complex sequential data more effectively than classical approaches. However, their practical advantage over established classical methods remains uncertain. In this work, we present a comprehensive benchmark study comparing a range of variational quantum algorithms (VQAs) and classical machine learning models for time series forecasting. We evaluate their predictive performance on three chaotic systems across 27 time series prediction tasks of varying complexity, and ensure a fair comparison through extensive hyperparameter optimization. Our results indicate that, in many cases, quantum models struggle to match the accuracy of simple classical counterparts of comparable complexity. Furthermore, we analyze the predictive performance relative to the model complexity and discuss the practical limitations of VQAs for time series forecasting.

arXiv:2504.12416•Machine Learning Science and Technology•Jan 9, 2026•21 citations

Quantum next generation reservoir computing: an efficient quantum algorithm for forecasting quantum dynamics

Apimuk Sornsaeng, Ninnat Dangniam, Thiparat Chotibut

Next Generation Reservoir Computing (NG-RC) is a modern class of model-free machine learning that enables an accurate forecasting of time series data generated by dynamical systems. We demonstrate that NG-RC can accurately predict full many-body quantum dynamics in both integrable and chaotic systems. This is in contrast to the conventional application of reservoir computing that concentrates on the prediction of the dynamics of observables. In addition, we apply a technique which we refer to as skipping ahead to predict far future states accurately without the need to extract information about the intermediate states. However, adopting a classical NG-RC for many-body quantum dynamics prediction is computationally prohibitive due to the large Hilbert space of sample input data. In this work, we propose an end-to-end quantum algorithm for many-body quantum dynamics forecasting with a quantum computational speedup via the block-encoding technique. This proposal presents an efficient model-free quantum scheme to forecast quantum dynamics coherently, bypassing inductive biases incurred in a model-based approach.

arXiv:2308.14239•Quantum Machine Intelligence•Sep 9, 2024•18 citations

Forecasting long-time dynamics in quantum many-body systems by dynamic mode decomposition

Ryui Kaneko, Masatoshi Imada, Yoshiyuki Kabashima +1 more

Reliable numerical computation of quantum dynamics is a fundamental challenge when the long-ranged quantum entanglement plays essential roles as in the cases governed by quantum criticality in strongly correlated systems. Here we apply a method that utilizes reliable short-time data of physical quantities to accurately forecast long-time behavior of the strongly entangled systems. We straightforwardly employ the simple dynamic mode decomposition (DMD), which is commonly used in fluid dynamics. Despite the simplicity of the method, the effectiveness and applicability of the DMD in quantum many-body systems such as the Ising model in the transverse field at the critical point are demonstrated, even when the time evolution at long time exhibits complicated features such as a volume-law entanglement entropy and consequential power-law decays of correlations characteristic of systems with long-ranged quantum entanglements unlike fluid dynamics. The present method, though simple, enables accurate forecasts amazingly at time as long as nearly an order of magnitude longer than that of the short-time training data. Effects of noise on the accuracy of the forecast are also investigated, because they are important especially when dealing with the experimental data. We find that a few percentages of noise do not affect the prediction accuracy destructively.

arXiv:2403.19947•Physical Review Research•Jan 23, 2025•17 citations

Forecasting Low-Dimensional Navier-Stokes equations via Multi-Dimensional Hybrid Quantum Reservoir Computing

L. Salatino, L. Mariani, A. Giordano +9 more

The prediction of complex dynamics remains an open problem across many domains of physics, where nonlinearities and multiscale interactions severely limit the reliability of conventional forecasting methods. Quantum reservoir computing (QRC) has emerged as a promising paradigm for information processing by exploiting the high dimensionality of the Hilbert space, where the dynamics of quantum systems take place. Here, we introduce a hybrid quantum-classical reservoir architecture capable of handling multivariate time series through quantum evolution combined with classical memory enhancement. Our model employs a five-qubit transverse-field Ising Hamiltonian with input-modulated dynamics and temporal multiplexing, enabling the encoding of input signals over multiple timescales. We apply this framework to two paradigmatic models of chaotic behavior in fluid dynamics, where multiscale dynamics and nonlinearities play a dominant role: a low-dimensional truncation of the two-dimensional Navier-Stokes equations and the Lorenz-63 system. By systematically scanning the quantum system's parameter space, we identify regions that maximize forecasting performance, as measured by the Valid Prediction Time. The observed robustness and reliable performances for both dynamical systems suggest that this hybrid quantum approach offers a flexible platform for modelling complex nonlinear time series.

quant-pharXiv:2509.04006•Chaos An Interdisciplinary Journal of Nonlinear Science•Sep 5, 2025•5 citations

Optimizing quantum noise-induced reservoir computing for nonlinear and chaotic time series prediction

Daniel Fry, Amol A. Deshmukh, Samuel Yen-Chi Chen +2 more

Quantum reservoir computing is strongly emerging for sequential and time series data prediction in quantum machine learning. We make advancements to the quantum noise-induced reservoir, in which reservoir noise is used as a resource to generate expressive, nonlinear signals that are efficiently learned with a single linear output layer. We address the need for quantum reservoir tuning with a novel and generally applicable approach to quantum circuit parameterization, in which tunable noise models are programmed to the quantum reservoir circuit to be fully controlled for effective optimization. Our systematic approach also involves reductions in quantum reservoir circuits in the number of qubits and entanglement scheme complexity. We show that with only a single noise model and small memory capacities, excellent simulation results were obtained on nonlinear benchmarks that include the Mackey-Glass system for 100 steps ahead in the challenging chaotic regime.

arXiv:2303.05488•Scientific Reports•Nov 7, 2023•35 citations

Quantum Entanglement Time Scale Prediction Model

Jincheng Zhang

This paper introduces a novel time scale prediction model based on quantum entanglement, aiming to elucidate the underlying mechanisms governing complex systems. We propose a "time-space entanglement" model, employing dynamic state evolution simulations to predict system behavior and subsequently translate these predictions into a connection with classical physics. The model leverages the non-locality inherent in quantum entanglement to offer a fundamentally different approach to time scale estimation, potentially revolutionizing the simulation of complex systems. This work addresses the crucial challenge of accurately forecasting the evolution of systems exhibiting quantum phenomena, offering a new pathway for understanding and controlling complex quantum behavior.

•Sep 5, 2026•0 citations
Accurately simulating chaotic quantum many-body dynamics remains a major computational challenge for classical methods, due to the rapid buildup and spatial spreading of entanglement during the evolution. This raises the question of whether machine learning can provide an effective alternative for predicting quantum dynamics. We address this question by formulating quantum dynamics as a time-series forecasting problem, using a few-qubit PXP chain, realizable with Rydberg-atom arrays, as a benchmark. By varying the initial state, the system spans dynamical regimes ranging from ergodic behavior to quantum many-body scarring, providing a controlled setting for testing forecasting models across qualitatively different dynamics. We compare two contrasting architectures: an expressive nonlinear Transformer and DLinear, a simple linear forecasting model. The Transformer accurately predicts dynamics in the more ergodic regime, but its performance progressively deteriorates as the initial state approaches the scarred limit. In contrast, DLinear remains accurate across the entire family of initial states, with its main deviations consisting of small high-frequency oscillations that have little effect on the overall prediction error. Remarkably, these results show that observables generated by complex quantum many-body dynamics can be forecast with high accuracy through a simple linear mapping from past to future observations. This reveals that the complexity of the underlying quantum evolution need not translate into an equally complex forecasting problem.
The paper asks whether forecasting observables of chaotic quantum many-body dynamics requires an expressive nonlinear model. It compares DLinear, a linear time-series forecasting architecture, with an autoregressive Transformer on a PXP chain exhibiting both thermalizing and quantum-scarred dynamics.
The benchmark uses exact evolution of an L=10L=10L=10 open chain for 500 initial states sampled from a two-parameter family interpolating between polarized and Néel configurations, including entangled superpositions. Each trajectory contains 55 features: local magnetizations and all connected two-site zzzzzz correlations. Models receive 500 samples covering t∈[0,10)t\in[0,10)t∈[0,10) and predict 300 samples over t∈[10,16)t\in[10,16)t∈[10,16), with Δt=0.02\Delta t=0.02Δt=0.02. There are 400 training/validation trajectories and 100 held-out test trajectories. Both models use a loss penalizing value errors and discrepancies in temporal increments and directions; DLinear predicts the entire horizon directly, whereas the Transformer generates it recursively.
DLinear yields low, comparatively uniform mean absolute errors across the initial-state family. Its raw directional accuracy is approximately 50%50\%50%, attributed to small high-frequency prediction artifacts; smoothing raises it above 90%90\%90% across much of parameter space. Transformer errors increase toward the scarred regime, with local absolute errors approaching 0.70.70.7 in the selected worst-case trajectory. Its error grows more strongly over the forecast horizon.
The stated limitations are the single finite chain, restricted initial-state family, selected observables, and fixed forecasting horizon. Generalization to other Hamiltonians, larger systems, circuits, and open-system dynamics remains unestablished.
Abstract Variational quantum machine learning algorithms have been proposed as promising tools for time series prediction, with the potential to handle complex sequential data more effectively than classical approaches. However, their practical advantage over established classical methods remains uncertain. In this work, we present a comprehensive benchmark study comparing a range of variational quantum algorithms (VQAs) and classical machine learning models for time series forecasting. We evaluate their predictive performance on three chaotic systems across 27 time series prediction tasks of varying complexity, and ensure a fair comparison through extensive hyperparameter optimization. Our results indicate that, in many cases, quantum models struggle to match the accuracy of simple classical counterparts of comparable complexity. Furthermore, we analyze the predictive performance relative to the model complexity and discuss the practical limitations of VQAs for time series forecasting.
Next Generation Reservoir Computing (NG-RC) is a modern class of model-free machine learning that enables an accurate forecasting of time series data generated by dynamical systems. We demonstrate that NG-RC can accurately predict full many-body quantum dynamics in both integrable and chaotic systems. This is in contrast to the conventional application of reservoir computing that concentrates on the prediction of the dynamics of observables. In addition, we apply a technique which we refer to as skipping ahead to predict far future states accurately without the need to extract information about the intermediate states. However, adopting a classical NG-RC for many-body quantum dynamics prediction is computationally prohibitive due to the large Hilbert space of sample input data. In this work, we propose an end-to-end quantum algorithm for many-body quantum dynamics forecasting with a quantum computational speedup via the block-encoding technique. This proposal presents an efficient model-free quantum scheme to forecast quantum dynamics coherently, bypassing inductive biases incurred in a model-based approach.
Reliable numerical computation of quantum dynamics is a fundamental challenge when the long-ranged quantum entanglement plays essential roles as in the cases governed by quantum criticality in strongly correlated systems. Here we apply a method that utilizes reliable short-time data of physical quantities to accurately forecast long-time behavior of the strongly entangled systems. We straightforwardly employ the simple dynamic mode decomposition (DMD), which is commonly used in fluid dynamics. Despite the simplicity of the method, the effectiveness and applicability of the DMD in quantum many-body systems such as the Ising model in the transverse field at the critical point are demonstrated, even when the time evolution at long time exhibits complicated features such as a volume-law entanglement entropy and consequential power-law decays of correlations characteristic of systems with long-ranged quantum entanglements unlike fluid dynamics. The present method, though simple, enables accurate forecasts amazingly at time as long as nearly an order of magnitude longer than that of the short-time training data. Effects of noise on the accuracy of the forecast are also investigated, because they are important especially when dealing with the experimental data. We find that a few percentages of noise do not affect the prediction accuracy destructively.
The prediction of complex dynamics remains an open problem across many domains of physics, where nonlinearities and multiscale interactions severely limit the reliability of conventional forecasting methods. Quantum reservoir computing (QRC) has emerged as a promising paradigm for information processing by exploiting the high dimensionality of the Hilbert space, where the dynamics of quantum systems take place. Here, we introduce a hybrid quantum-classical reservoir architecture capable of handling multivariate time series through quantum evolution combined with classical memory enhancement. Our model employs a five-qubit transverse-field Ising Hamiltonian with input-modulated dynamics and temporal multiplexing, enabling the encoding of input signals over multiple timescales. We apply this framework to two paradigmatic models of chaotic behavior in fluid dynamics, where multiscale dynamics and nonlinearities play a dominant role: a low-dimensional truncation of the two-dimensional Navier-Stokes equations and the Lorenz-63 system. By systematically scanning the quantum system's parameter space, we identify regions that maximize forecasting performance, as measured by the Valid Prediction Time. The observed robustness and reliable performances for both dynamical systems suggest that this hybrid quantum approach offers a flexible platform for modelling complex nonlinear time series.
Quantum reservoir computing is strongly emerging for sequential and time series data prediction in quantum machine learning. We make advancements to the quantum noise-induced reservoir, in which reservoir noise is used as a resource to generate expressive, nonlinear signals that are efficiently learned with a single linear output layer. We address the need for quantum reservoir tuning with a novel and generally applicable approach to quantum circuit parameterization, in which tunable noise models are programmed to the quantum reservoir circuit to be fully controlled for effective optimization. Our systematic approach also involves reductions in quantum reservoir circuits in the number of qubits and entanglement scheme complexity. We show that with only a single noise model and small memory capacities, excellent simulation results were obtained on nonlinear benchmarks that include the Mackey-Glass system for 100 steps ahead in the challenging chaotic regime.
This paper introduces a novel time scale prediction model based on quantum entanglement, aiming to elucidate the underlying mechanisms governing complex systems. We propose a "time-space entanglement" model, employing dynamic state evolution simulations to predict system behavior and subsequently translate these predictions into a connection with classical physics. The model leverages the non-locality inherent in quantum entanglement to offer a fundamentally different approach to time scale estimation, potentially revolutionizing the simulation of complex systems. This work addresses the crucial challenge of accurately forecasting the evolution of systems exhibiting quantum phenomena, offering a new pathway for understanding and controlling complex quantum behavior.