quantum-machine-learning

Titans-QFWP is a hybrid reinforcement learning architecture integrating a Quantum Fast Weight Programmer with Titans-style memory for adaptive portfolio optimization, achieving strong performance on S&P 500 stocks.

The paper empirically characterizes the learning geometry of hybrid quantum forecasting models, comparing them to classical baselines using Neural Tangent Kernel dynamics and other metrics, showing that similar generalization can emerge from different optimization trajectories.

Researchers developed Quantum Elastic Weight Consolidation (QEWC), a framework that uses Quantum Fisher Information to help quantum AI systems retain knowledge during sequential learning, reducing catastrophic forgetting.

Proposes Parallel Quantum Feature Augmentation (PQFA), a hybrid quantum-classical framework that applies shallow variational quantum circuits to enhance fused multimodal features, outperforming classical baselines with fewer parameters.

Introduces Quantum Port-Hamiltonian Neural Networks (Q-pHNNs) that learn classical dynamics while preserving conservation and dissipation properties using quantum circuits with measurement-induced nonlinearity. Experiments show low energy drift and accurate damping coefficient identification.

LMU researchers developed a Quantum Boltzmann Machine model for pneumonia detection from chest X-rays. Using fewer than 9,000 parameters (vs. millions in classical CNNs), the model achieves 84–86% accuracy, demonstrating potential advantages of quantum machine learning for small medical datasets.

This paper presents a fair-comparison study of variational quantum circuits in diffusion models, introducing a squeeze-and-excitation scaffold to isolate quantum contributions. It finds functional parity with classical controls and identifies angle-embedding failures in score-based settings, offering a rigorous methodology and mechanistic analysis.

Proposes a low-overhead error correction technique for quantum convolutional neural networks using bivariate bicycle codes, demonstrating improved learning under realistic noise compared to unprotected QCNNs.

This paper proposes active shot allocation strategies for quantum kernel estimation in Gaussian process regression, deriving pair-level sensitivities to guide non-uniform shot budgets and demonstrating significant improvements in test RMSE over uniform allocation on benchmarks.

This paper presents a quantum autoencoder for compression-driven anomaly detection in brain MRI, achieving high ROC-AUC scores and outperforming classical baselines while providing interpretable anomaly heatmaps.

QDiffusion-TS is the first quantum generative diffusion model for real-world time series synthesis, replacing feed-forward components in a denoising transformer with quantum neural networks. It reduces trainable parameters by nearly three orders of magnitude and improves Wasserstein distance by 44% on financial data, with downstream forecasting gains up to 71% in RMSE.

Lecture notes on the foundations of quantum machine learning, covering qubits, superposition, measurement, and the Bloch sphere.

This paper proposes a hybrid classical-quantum variational autoencoder for neural topic modeling, embedding parameterized quantum circuits in the inference network. Experiments on the AgNews dataset demonstrate improved topic coherence and diversity compared to state-of-the-art classical models, showing viability on NISQ-era quantum devices.

This paper proposes a hybrid quantum-classical workflow for plant phenomics classification under small-data regimes, using supervised latent restructuring (PCA + LDA) to improve geometric separability before quantum kernel alignment. Experiments show improved separability but highlight compression trade-offs and the difficulty of achieving strong quantum performance.

A survey on quantum adversarial machine learning, covering attacks, defenses, and theoretical underpinnings.

This paper presents empirical evidence that quantum entanglement provides a measurable advantage in multi-agent reinforcement learning, using the CHSH game and cooperative navigation tasks to demonstrate performance improvements over classical baselines.