Hamiltonian Learning via Inverse Physics-Informed Neural Networks

Abstract

Hamiltonian learning (HL), enabling precise estimation of system parameters and underlying dynamics, plays a critical role in characterizing quantum systems. However, conventional HL methods face challenges in noise robustness and resource efficiency, especially under limited measurements. In this work, we present \textit{Inverse Physics-Informed Neural Networks for Hamiltonian Learning (iPINN-HL)}, an approach that incorporates the Schrödinger equation as a soft constraint via a loss function penalty into the ML procedure. This formulation allows the model to integrate both observational data and known physical laws to infer Hamiltonian parameters with greater accuracy and resource efficiency. We benchmark iPINN-HL against a deep-neural-network-based quantum state tomography method (denoted as DNN-HL) and demonstrate its effectiveness across several different scenarios, including one-dimensional spin chains, cross-resonance gate calibration, crosstalk identification, and real-time compensation to parameter drift. Our results show that iPINN-HL can approach the Heisenberg limit and exhibits robustness to noises, while outperforming DNN-HL in accuracy and resource efficiency. Therefore, iPINN-HL is a powerful and flexible framework for quantum system characterization for practical tasks.

18 pages, 11 figures

References in corpus (22)

• Quantum error correction below the surface code threshold
• High-threshold and low-overhead fault-tolerant quantum memory
• Quantum Process Tomography: Resource Analysis of Different Strategies
• Laser-annealing Josephson junctions for yielding scaled-up superconducting quantum processors
• Mitigating depolarizing noise on quantum computers with noise-estimation circuits
• Model-Free Quantum Control with Reinforcement Learning
• Reliable extrapolation of deep neural operators informed by physics or sparse observations
• Quantum crosstalk analysis for simultaneous gate operations on superconducting qubits
• Benchmarking a trapped-ion quantum computer with 30 qubits
• Integrated tool-set for Control, Calibration and Characterization of quantum devices applied to superconducting qubits
• Robust control and optimal Rydberg states for neutral atom two-qubit gates
• Robust and Efficient Hamiltonian Learning
• Practical Black Box Hamiltonian Learning
• Complete characterization of quantum correlations by randomized measurements
• Control and mitigation of microwave crosstalk effect with superconducting qubits
• The advantage of quantum control in many-body Hamiltonian learning
• Active Physics Informed Deep Learning: Surrogate Modeling for Non Planar Wavefront Excitation of Topological Nanophotonic Devices
• Active Learning of Quantum System Hamiltonians yields Query Advantage
• SPAM-Robust Multi-axis Quantum Noise Spectroscopy in Temporally Correlated Environments
• Universal Robust Geometric Quantum Control via Geometric Trajectory Correction
• Unified Quantum State Tomography and Hamiltonian Learning Using Transformer Models: A Language-Translation-Like Approach for Quantum Systems
• Hamiltonian Learning using Machine Learning Models Trained with Continuous Measurements