Hamiltonian Learning using Machine Learning Models Trained with Continuous Measurements
arXiv:2404.05526 · doi:10.1103/PhysRevApplied.22.044080
Abstract
We build upon recent work on using Machine Learning models to estimate Hamiltonian parameters using continuous weak measurement of qubits as input. We consider two settings for the training of our model: (1) supervised learning where the weak measurement training record can be labeled with known Hamiltonian parameters, and (2) unsupervised learning where no labels are available. The first has the advantage of not requiring an explicit representation of the quantum state, thus potentially scaling very favorably to larger number of qubits. The second requires the implementation of a physical model to map the Hamiltonian parameters to a measurement record, which we implement using an integrator of the physical model with a recurrent neural network to provide a model-free correction at every time step to account for small effects not captured by the physical model. We test our construction on a system of two qubits and demonstrate accurate prediction of multiple physical parameters in both the supervised and unsupervised context. We demonstrate that the model benefits from larger training sets establishing that it is in fact "learning," and we show robustness to errors in the assumed physical model by achieving accurate parameter estimation in the presence of unanticipated single particle relaxation.
v2. Updated to published version
References in corpus (27)
- Quantum Computing in the NISQ era and beyond
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- The density-matrix renormalization group in the age of matrix product states
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- Circuit Quantum Electrodynamics
- Deep learning for universal linear embeddings of nonlinear dynamics
- Time-dependent variational principle for quantum lattices
- Unifying time evolution and optimization with matrix product states
- A Straightforward Introduction to Continuous Quantum Measurement
- Reconstructing quantum states with generative models
- Quantum trajectory approach to circuit QED: Quantum jumps and the Zeno effect
- Maximum Likelihood, Minimum Effort
- Detecting crosstalk errors in quantum information processors
- Learning a local Hamiltonian from local measurements
- Suppression of crosstalk in superconducting qubits using dynamical decoupling
- Constructing exact representations of quantum many-body systems with deep neural networks
- Sample-efficient learning of quantum many-body systems
- Using a Recurrent Neural Network to Reconstruct Quantum Dynamics of a Superconducting Qubit from Physical Observations
- Discovery of Physics from Data: Universal Laws and Discrepancies
- Learning hard quantum distributions with variational autoencoders
- Learning many-body Hamiltonians with Heisenberg-limited scaling
- Modelling Non-Markovian Quantum Processes with Recurrent Neural Networks
- General method for extracting the quantum efficiency of dispersive qubit readout in circuit QED
- Learning the dynamics of open quantum systems from their steady states
- Optimal learning of quantum Hamiltonians from high-temperature Gibbs states
- Quantum-tailored machine-learning characterization of a superconducting qubit
- Unified Quantum State Tomography and Hamiltonian Learning Using Transformer Models: A Language-Translation-Like Approach for Quantum Systems