Physics-informed time series analysis with Kolmogorov-Arnold Networks under Ehrenfest constraints

Abstract

The prediction of quantum dynamical responses lies at the heart of modern physics. Yet, modeling these time-dependent behaviors remains a formidable challenge because quantum systems evolve in high-dimensional Hilbert spaces, often rendering traditional numerical methods computationally prohibitive. While large language models have achieved remarkable success in sequential prediction, quantum dynamics presents a fundamentally different challenge: forecasting the entire temporal evolution of quantum systems rather than merely the next element in a sequence. Existing neural architectures such as recurrent and convolutional networks often require vast training datasets and suffer from spurious oscillations that compromise physical interpretability. In this work, we introduce a fundamentally new approach: Kolmogorov Arnold Networks (KANs) augmented with physics-informed loss functions that enforce the Ehrenfest theorems. Our method achieves superior accuracy with significantly less training data: it requires only 5.4 percent of the samples (200) compared to Temporal Convolution Networks (3,700). We further introduce the Chain of KANs, a novel architecture that embeds temporal causality directly into the model design, making it particularly well-suited for time series modeling. Our results demonstrate that physics-informed KANs offer a compelling advantage over conventional black-box models, maintaining both mathematical rigor and physical consistency while dramatically reducing data requirements.

References in corpus (21)

• Classical simulation of infinite-size quantum lattice systems in one spatial dimension
• A Survey on Kolmogorov-Arnold Network
• Distributed physics informed neural network for data-efficient solution to partial differential equations
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Operational Dynamic Modeling Transcending Quantum and Classical Mechanics
• Stochastic Physics-Informed Neural Ordinary Differential Equations
• High-harmonic generation by electric polarization, spin current, and magnetization
• High-harmonic generation in quantum spin systems
• Driven Imposters: Controlling Expectations in Many-Body Systems
• Making Distinct Dynamical Systems Appear Spectrally Identical
• Wigner-Lindblad equations for quantum friction
• Purifying electron spectra from noisy pulses with machine learning using synthetic Hamilton matrices
• Dirac open quantum system dynamics: formulations and simulations
• Non-conservative Forces via Quantum Reservoir Engineering
• Deep learning and high harmonic generation
• No thermalization without correlations
• Sequential optical response suppression for chemical mixture characterization
• Decoherence-Free Entropic Gravity: Model and Experimental Tests
• Operational Dynamical Modeling of spin 1/2 relativistic particles: the Dirac equation and its classical limit
• Decoherence-Free Entropic Gravity for Dirac Fermion
• Input-Output Optics as a Causal Time Series Mapping: A Generative Machine Learning Solution