When Quantum Meets AI: Quantum Methods for Machine Learning and Machine Learning Methods for Quantum Systems
quant-ph, cs.AI
Submitted: 2026-09-22
Updated: 2026-09-22
Comments: 171 pages, 28 figures, PhD thesis
Code: https://github.com/takh04/neural-quantum-embedding
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
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.
Sources
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- QRAM: A Survey and Critique
- A Quantum Approximate Optimization Algorithm
- Quantum Convolutional Neural Networks are Effectively Classically Simulable
- Neural quantum embedding via deterministic quantum computation with one qubit
- Understanding Generalization in Quantum Machine Learning with Margins
- A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
- Predicting the Generalization Gap in Deep Networks with Margin Distributions
- Fantastic Generalization Measures and Where to Find Them
- Rademacher complexity of noisy quantum circuits
- Information-theoretic generalization bounds for learning from quantum data
- Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
- PennyLane: Automatic differentiation of hybrid quantum-classical computations
- Quantum embeddings for machine learning
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Deep Learning for Classical Japanese Literature
- Scalable Neural Decoders for Practical Real-Time Quantum Error Correction
Related papers
- Reconquering Bell sampling on qudits: stabilizer learning and testing, quantum pseudorandomness bounds, and more
- Encrypted clones can leak: Classification of informative subsets in Quantum Encrypted Cloning
- Polynomial-time classical and quantum simulation of quantum impurity models
- Theory of quantum-enhanced interferometry with general Markovian light sources
- A convergent hierarchy of spectral gap certificates for qubit Hamiltonians
- Universal Bound and Phase Transition in Many-Body Fermionic Non-Gaussianity