Quantum Machine Learning Approaches

Abstract

Quantum machine learning sits at the intersection of quantum computing and artificial intelligence, seeking to exploit quantum mechanical phenomena -- superposition, entanglement, and interference -- to achieve computational advantages for learning tasks. This study presents a systematic evaluation of five quantum ML approaches -- variational quantum classifiers (VQC), quantum kernel methods, quantum reservoir computing, quantum Boltzmann machines, and hybrid quantum-classical neural networks -- benchmarked against classical counterparts on both simulated quantum hardware (up to 30 qubits) and real NISQ devices (IBM Quantum, 27 qubits). Evaluations spanned four task categories: binary classification on structured datasets (6 UCI benchmarks), quantum chemistry property prediction (QM9 molecular energies), generative modelling (learning probability distributions), and optimisation (Max-Cut on random graphs). A total of 1,920 experiments were conducted. On classical structured datasets, no quantum method outperformed the best classical baseline (XGBoost or SVM) at any problem size accessible to current quantum hardware (up to 30 features), with quantum kernel methods achieving parity at 0.4 +- 0.8% accuracy difference but at 100-1000x higher computational cost. On quantum chemistry, variational quantum eigensolvers showed a genuine advantage for small molecules (H2, LiH, BeH2): achieving chemical accuracy (1 kcal/mol) with 4-12 qubits where classical methods required exponentially more compute for equivalent accuracy. Noise on real NISQ devices degraded all quantum ML methods by 8.4-22.6% relative to noiseless simulation, with error mitigation recovering 42-68% of the noise-induced loss. The quantum advantage threshold -- the problem size at which quantum methods become faster than classical for equivalent accuracy-- was estimated at 50-100 logical qubits for quantum chemistry and 200+ logical qubits for general ML tasks, placing practical quantum ML advantage beyond current NISQ capabilities but within plausible reach of fault-tolerant devices. A practical assessment framework mapping task type, problem structure, and available quantum hardware to expected quantum advantage is proposed