When Quantum Meets AI: Quantum Methods for Machine Learning and Machine Learning Methods for Quantum Systems

Abstract

This thesis studies the intersection of quantum computing and artificial intelligence in two directions: quantum methods for machine learning and machine learning methods for quantum systems. For quantum machine learning, Neural Quantum Embedding learns data representations that increase the trace distance between embedded class ensembles, lowering an embedding-dependent bound on empirical risk and improving classification on noisy quantum hardware. A training objective based on the Hilbert-Schmidt inner product extends this approach to deterministic quantum computation with one qubit (DQC1) and is demonstrated on an NMR quantum processor. A margin-based generalization analysis then connects quantum neural network performance to quantum state discrimination. In the studied benchmarks, margin distributions predict generalization more reliably than parameter-count metrics. For quantum systems, a Mamba-based neural decoder for surface codes matches a reproduced Transformer baseline in memory experiments while reducing inference-cost scaling from quartic to quadratic in code distance. Under an explicit decoder-induced-noise model, it achieves lower logical error rates and a higher effective threshold. For neural quantum states, stochastic reconfiguration is interpreted as tangent-space ridge regression, with its diagonal shift controlling the bias-variance trade-off under finite Monte Carlo sampling. Multi-shift stochastic reconfiguration reduces checkpoint-local validation residuals and update variance relative to fixed-shift SR, at additional computational cost. Together, these contributions show how learned representations, statistical control, and hardware constraints shape the exchange between quantum computing and machine learning.

Generative Quantum Machine Learning Methods for Cancer Detection using Augmented Datasets
Sophia Knutson, Nandika Goyal, Gennaro De Luca +3
arXiv10 Oct 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
Harnessing Machine Learning and Composite Quantum Chemical Methods for Computing Accurate Bond Dissociation Energies of PFAS
Kalpak Ghosh, Samir Kumar Nayak, Rohit Batra +1
ChemRxiv28 Sep 2026PreprintCC BY-NC-NDFull textAtomic, molecular & optical physicsChemRxiv
Qmes: Quantum Meta-Learning for Encoding Selection in Quantum Kernel Methods
Dao Duy Tung, Quoc Chuong Nguyen, Vu Tuan Hai +2
arXiv4 Sep 2026PreprintCC BY 4.0Full textQuantum physics & quantum informationarXiv
Quantum Simulation of Nuclear Shell Model Using GCM-Based Methods on NISQ Devices
Durgesh Pandey, Ashutosh Singh, Ankit Kumar Das +1
HAL1 Sep 2026PreprintLicence not statedNuclear physics Quantum physics & quantum informationHAL
Machine Learning for High-Entropy Catalysts: Methods and Applications
Hao Chen, Zongrui Pei, Xianglin Liu
arXiv21 Oct 2026PreprintCC BY 4.0Full textCondensed matterarXiv

Cite

BibTeX RIS

BibTeX

@misc{hur2026when,
  title = {{When Quantum Meets AI: Quantum Methods for Machine Learning and Machine Learning Methods for Quantum Systems}},
  author = {Tak Hur},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.25641},
  eprint = {2609.25641},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.25641},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - When Quantum Meets AI: Quantum Methods for Machine Learning and Machine Learning Methods for Quantum Systems
AU  - Tak Hur
PY  - 2026
DA  - 2026/09/22
PB  - arXiv
DO  - 10.48550/arxiv.2609.25641
UR  - https://arxiv.org/abs/2609.25641
AB  - This thesis studies the intersection of quantum computing and artificial intelligence in two directions: quantum methods for machine learning and machine learning methods for quantum systems. For quantum machine learning, Neural Quantum Embedding learns data representations that increase the trace distance between embedded class ensembles, lowering an embedding-dependent bound on empirical risk and improving classification on noisy quantum hardware. A training objective based on the Hilbert-Schmidt inner product extends this approach to deterministic quantum computation with one qubit (DQC1) and is demonstrated on an NMR quantum processor. A margin-based generalization analysis then connects quantum neural network performance to quantum state discrimination. In the studied benchmarks, margin distributions predict generalization more reliably than parameter-count metrics. For quantum systems, a Mamba-based neural decoder for surface codes matches a reproduced Transformer baseline in memory experiments while reducing inference-cost scaling from quartic to quadratic in code distance. Under an explicit decoder-induced-noise model, it achieves lower logical error rates and a higher effective threshold. For neural quantum states, stochastic reconfiguration is interpreted as tangent-space ridge regression, with its diagonal shift controlling the bias-variance trade-off under finite Monte Carlo sampling. Multi-shift stochastic reconfiguration reduces checkpoint-local validation residuals and update variance relative to fixed-shift SR, at additional computational cost. Together, these contributions show how learned representations, statistical control, and hardware constraints shape the exchange between quantum computing and machine learning.
ER  -

Abstract

Related

Cite