Physics-Constrained Conditional Generative Learning for Quantum State and Process Tomography
Abstract
Quantum state and process tomography constitute essential diagnostic tools in quantum information science, yet their standard formulations suffer from prohibitive computational scaling as the number of qubits grows. In this work, we introduce a physics-constrained conditional generative adversarial network that bypasses iterative constrained inversion by directly learning a forward generative mapping conditioned on Pauli expectation values. The generator embeds a differentiable Cholesky layer at its output, which enforces Hermiticity, positive semidefiniteness, and unit trace by construction. Our experiments reveal that the strength of the L1 penalty critically governs the emergence of GHZ coherence during training: an excessively large penalty postpones the coherence onset and yields a prolonged low-fidelity plateau, whereas an intermediate value enables the fastest stable convergence. Moreover, for high-temperature thermal states, an over-complete measurement basis proves necessary to prevent sustained late-stage fluctuations. By extending the same Cholesky constraint to the Choi-matrix representation, the framework naturally accommodates quantum process tomography. For systems with n ≥ 6 qubits, the exponential growth of the underlying 2n × 2n density matrix remains the fundamental bottleneck; we discuss how integrating tensor-network structures can contain the per-iteration cost while preserving reconstruction fidelity. Altogether, these results suggest that physically constrained generative learning offers a scalable and amortizable pathway toward data-driven tomography for noisy intermediate-scale quantum devices.
Related
- Physics-Transfer Learning: A Physics-Constrained Theory for Zero-Shot Generalization Along the Ladder of Complexity
- A physics-constrained machine-learning sub-grid-scale modeling approach for turbulent premixed flames
- Physics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography
- NuPaD: A Generative AI Framework for Fostering Deep Learning in Subatomic Physics
- Physics-Constrained Learning of Dose-Dependent Spectral Degradation in Metal--Organic Frameworks from In Situ Low-Loss EELS
BibTeX
@misc{li2026physicsconstrained,
title = {{Physics-Constrained Conditional Generative Learning for Quantum State and Process Tomography}},
author = {Daming Li and Luhao Shi},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.28035},
eprint = {2608.28035},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28035},
}
RIS
TY - UNPB
TI - Physics-Constrained Conditional Generative Learning for Quantum State and Process Tomography
AU - Daming Li
AU - Luhao Shi
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2608.28035
UR - https://arxiv.org/abs/2608.28035
AB - Quantum state and process tomography constitute essential diagnostic tools in quantum information science, yet their standard formulations suffer from prohibitive computational scaling as the number of qubits grows. In this work, we introduce a physics-constrained conditional generative adversarial network that bypasses iterative constrained inversion by directly learning a forward generative mapping conditioned on Pauli expectation values. The generator embeds a differentiable Cholesky layer at its output, which enforces Hermiticity, positive semidefiniteness, and unit trace by construction. Our experiments reveal that the strength of the L^1 penalty critically governs the emergence of GHZ coherence during training: an excessively large penalty postpones the coherence onset and yields a prolonged low-fidelity plateau, whereas an intermediate value enables the fastest stable convergence. Moreover, for high-temperature thermal states, an over-complete measurement basis proves necessary to prevent sustained late-stage fluctuations. By extending the same Cholesky constraint to the Choi-matrix representation, the framework naturally accommodates quantum process tomography. For systems with n ≥ 6 qubits, the exponential growth of the underlying 2^n × 2^n density matrix remains the fundamental bottleneck; we discuss how integrating tensor-network structures can contain the per-iteration cost while preserving reconstruction fidelity. Altogether, these results suggest that physically constrained generative learning offers a scalable and amortizable pathway toward data-driven tomography for noisy intermediate-scale quantum devices.
ER -