arXiv:2606. 15213v1 Announce Type: cross Abstract: Time series forecasting largely benefits from combining the strengths of different models, especially using a scheme where a model corrects another model by capturing supplementary patterns from forecasting errors.
arXiv:2604. 08277v3 Announce Type: replace-cross Abstract: We present QARIMA, a quantum state-similarity-based reconstruction of the classical ARIMA modelling pipeline.
arXiv:2607. 16358v1 Announce Type: cross Abstract: This paper presents a unified quantum-classical hybrid framework for multi-horizon time-series forecasting, introducing two model variants Quantum Reservoir Forecaster (QRC-F) and Variational Quantum Forecaster (VQF-F).
arXiv:2607. 24399v1 Announce Type: cross Abstract: Multivariate time series forecasting (MTSF) predicts future values of multiple variables from historical data.
Multivariate time series forecasting (MTSF) predicts future values of multiple variables from historical data. While quantum neural networks have been increasingly applied to this task, they typically rely on fixed local measurements, which restrict their expressivity.
The paper introduces a recursive quantum long short-term memory (QLSTM) architecture and compares it to a standard QLSTM for one-step-ahead daily temperature forecasting. Using Toronto weather data and identical training settings, the recursive model consistently reaches near-optimal test loss earlier, achieves lower mean absolute error and root mean squared error, and shows a smaller generalization gap across input windows of 8, 16, and 32 days over 20 random seeds. These findings suggest that recursive quantum feature transformations can enhance stability and out-of-sample performance in compact hybrid quantum–classical temporal models.
arXiv:2608. 19497v1 Announce Type: new Abstract: We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline.
The paper presents a reproducible study of multi‑horizon forecasting on the Lomnicky Stit neutron monitor (LMKS) time series. It evaluates a range of models—from simple seasonal baselines to modern deep sequence models and quantum‑inspired architectures such as QiLSTM and QiKAN—using MAE and RMSE metrics. Results show that the quantum‑inspired KAN variant (QiKAN) achieves the lowest aggregate error, while the simple Seasonal Naive baseline remains highly competitive, indicating that strong seasonal or low‑dimensional functional priors can rival more complex models for highly periodic scientific data.
arXiv:2603. 09789v3 Announce Type: replace-cross Abstract: Accurate financial volatility forecasting is crucial but challenged by the non-linear, highly correlated nature of market data.
The paper evaluates hybrid quantum‑classical machine learning for predicting reduced‑order spatiotemporal brain deformation fields. Using Proper Orthogonal Decomposition to compress high‑dimensional displacement data, the authors compare static temporal‑to‑latent regression and autoregressive latent forecasting models. Classical neural networks outperform all quantum variants, though enhanced quantum circuits improve over minimal ones, indicating that classical architectures still hold a clear advantage in fidelity and stability for this task.
The paper presents a lightweight Quantum Prototypical Recurrent Unit (QPRU) that uses far fewer parameters than classical recurrent models like LSTM and GRU, as well as quantum variants such as QLSTM and QGRU. Despite its compactness, the QPRU matches state‑of‑the‑art forecasting performance. It offers structural and practical benefits, notably improved scalability and a reduced parameter count.
arXiv:2605. 18333v2 Announce Type: replace-cross Abstract: Accurate and efficient time-series forecasting remains a challenging problem for both classical and quantum neural architectures, particularly in multivariate environmental settings.
arXiv:2606. 27561v1 Announce Type: new Abstract: Generative models have achieved remarkable success in data synthesis, though recent advances driven by increasing model scale have introduced challenges in computational cost and efficiency.