Quantum Fast Weight Programming replaces explicit recurrence with a slow-to-fast programming mechanism that updates a shallow variational circuit at each time step. We study Quantum Fast Weight Programming applied to real-world physical time series in different forecasting regimes, emphasizing parameter-parity and transparent resource accounting. The model uses hardware-efficient, data re-uploading ansatzes and local observables, shifting temporal information into a tractable trajectory of circuit parameters. Under matched budgets, Quantum Fast Weight Programming attains competitive accuracy against quantum recurrent baselines and strong classical deep learning comparators, while substantially reducing the quantum gradient-evaluation burden associated with backpropagation through time. We managed to identify stable, NISQ-friendly configurations and clarify expressivity-trainability trade-offs. Obtained results position the proposed approach as a practical template for resource-aware sequential modeling in time series prediction and related signal processing domains.
Quantum Fast Weight Programming replaces explicit recurrence with a slow-to-fast programming mechanism that updates a shallow variational circuit at each time step. We study Quantum Fast Weight Programming applied to real-world physical time series in different forecasting regimes, emphasizing parameter-parity and transparent resource accounting. The model uses hardware-efficient, data re-uploading ansatzes and local observables, shifting temporal information into a tractable trajectory of circuit parameters. Under matched budgets, Quantum Fast Weight Programming attains competitive accuracy against quantum recurrent baselines and strong classical deep learning comparators, while substantially reducing the quantum gradient-evaluation burden associated with backpropagation through time. We managed to identify stable, NISQ-friendly configurations and clarify expressivity-trainability trade-offs. Obtained results position the proposed approach as a practical template for resource-aware sequential modeling in time series prediction and related signal processing domains.
Quantum Machine Learning (QML) has surfaced as a pioneering framework addressing sequential control tasks and time-series modeling. It has demonstrated empirical quantum advantages notably within domains such as Reinforcement Learning (RL) and time-series prediction. A significant advancement lies in Quantum Recurrent Neural Networks (QRNNs), specifically tailored for memory-intensive tasks encompassing partially observable environments and non-linear time-series prediction. Nevertheless, QRNN-based models encounter challenges, notably prolonged training duration stemming from the necessity to compute quantum gradients using backpropagation-through-time (BPTT). This predicament exacerbates when executing the complete model on quantum devices, primarily due to the substantial demand for circuit evaluation arising from the parameter-shift rule. This paper introduces the Quantum Fast Weight Programmers (QFWP) as a solution to the temporal or sequential learning challenge. The QFWP leverages a classical neural network (referred to as the ’slow programmer’) functioning as a quantum programmer to swiftly modify the parameters of a variational quantum circuit (termed the ’fast programmer’). Instead of completely overwriting the fast programmer at each time-step, the slow programmer generates parameter changes or updates for the quantum circuit parameters. This approach enables the fast programmer to incorporate past observations or information. Notably, the proposed QFWP model achieves learning of temporal dependencies without necessitating the use of quantum recurrent neural networks. Numerical simulations conducted in this study showcase the efficacy of the proposed QFWP model in both time-series prediction and RL tasks. The model exhibits performance levels either comparable to or surpassing those achieved by QLSTM-based models.
We propose a single-qubit Quantum Machine Learning (QML) model for time series forecasting, built around the concept of a Quantum Reupload Unit (QRU), a hardwareefficient quantum circuit architecture with shallow depth. The proposed model demonstrates enhanced predictive power compared to variational methods such as quantum circuits (VQC), parameterized quantum circuits (PQC), and quantum residual blocks (QRB). The proposed QRU outperforms classical learning models such as Recurrent Neural Networks (RNNs) and Long-Short Term Memory (LSTM) with the same number of parameters. The novelty of this approach is its ability to model temporal patterns without relying on an extensive memory state, which reduces resource demands while preserving forecast accuracy. The expressivity of the model is evaluated through Fourier spectral decomposition. We analyze the trainability of our model using the absorption witness metric. We benchmarked the proposed model on the Mackey-Glass chaotic time series and the real-world river level dataset from TAIAO. The proposed model consistently exhibits enhanced expressivity over both of the datasets. These results highlight the significance of QRUs as promising candidates for learning models that can be conveniently deployed on noisy intermediate-scale quantum (NISQ) hardware.
Accurate load forecasting is critical for effective energy management, infrastructure planning, and ensuring the stability of modern power systems. With growing interest in Quantum Computing (QC), recent efforts have demonstrated the applicability of Quantum Machine Learning (QML) across various domains, including supervised and unsupervised learning. However, the use of QML models for Time Series Forecasting (TSF) remains relatively underexplored. In this work, we present a complete framework for TSF based on Variational Quantum Algorithms (VQAs), capable of both single-step and multi-step ahead forecasting. We use tensor product encoding to encode the classical input samples into quantum states, and use the data re-uploading strategy to introduce temporal dependencies across each layer of the quantum circuit. Within this framework, we systematically evaluate multiple Variational Quantum Circuit (VQC) architectures to assess their suitability for forecasting problem. Among the tested configurations, thenLocaland its modified variantQuReUpconsistently outperformed other quantum ansatz designs. Notably, in recursive multi-step forecasting scenarios, these models not only matched but surpassed the performance of a classical Artificial Neural Network (ANN). For example, thenLocalmodel achieved a 8% reduction in mean absolute error (MAE) over ANN for a 24-hour horizon. These results underscore the potential of VQAs for efficient and accurate TSF, particularly in scenarios requiring short to medium-term predictions. The proposed framework offers a promising foundation for future research, including extensions to diverse datasets and deployment on real quantum hardware to study the impact of quantum noise and scalability.
Fast Weight Programmers (FWPs) encode temporal dependencies through dynamically updated parameters rather than recurrent hidden states. Quantum FWPs (QFWPs) extend this idea with variational quantum circuits (VQCs), but existing implementations rely on multi-qubit architectures that are difficult to scale on noisy intermediate-scale quantum (NISQ) devices and expensive to simulate classically. We propose gated QKAN-FWP, a fast-weight framework that integrates FWP with Quantum-inspired Kolmogorov-Arnold Network (QKAN) using single-qubit data re-uploading circuits as learnable nonlinear activation, known as DatA Re-Uploading ActivatioN (DARUAN). We further introduce a scalar-gated fast-weight update rule that stabilizes parameter evolution, supported by a theoretical analysis of its adaptive memory kernel, geometric boundedness, and parallelizable gradient paths. We evaluate the framework across time-series benchmarks, MiniGrid reinforcement learning, and highlight real-world solar cycle forecasting as our main practical result. In the long-horizon setting with 528-month input window and 132-month forecast horizon, our 12.5k-parameter model achieves lower scaled Mean Square Error (MSE), peak amplitude error, and peak timing error than a suite of classical recurrent baselines with up to 13x more parameters, including Long Short-Term Memory (LSTM) networks (25.9k-89.1k parameters), WaveNet-LSTM (167k), Vanilla recurrent neural network (11.5k), and a Modified Echo State Network (132k). To validate NISQ compatibility, we further deploy the trained fast programmer on IonQ and IBM Quantum processors, recovering forecasting accuracy within 0.1% relative MSE of the noiseless simulator at 1024 shots. These results position gated QKAN-FWP as a scalable, parameter-efficient, and NISQ-compatible approach to quantum-inspired sequence modeling.
This study introduces the Quantum-Train Quantum Fast Weight Programmer (QT-QFWP) framework, enabling efficient and scalable programming of variational quantum circuits (VQCs) through quantum-driven parameter updates for the classical slow programmer controlling the fast programmer VQC. By optimizing quantum and classical parameter management, QT-QFWP significantly reduces parameters (by 70–90%) compared to Quantum Long Short-Term Memory (QLSTM) and Quantum Fast Weight Programmer (QFWP) while maintaining accuracy. Benchmarking on time-series tasks—including Damped Simple Harmonic Motion (SHM), NARMA5, and Simulated Gravitational Waves (GW)—demonstrates superior efficiency and predictive accuracy. QT-QFWP is particularly advantageous for near-term quantum systems, addressing qubit and gate fidelity constraints, enhancing VQC deployment in time-sensitive applications, and expanding quantum computing’s role in machine learning.
Traffic matrices (TMs) capture network-wide origin-destination demand and are central to traffic engineering, yet accurate whole-matrix forecasting remains challenging when prediction must be performed under the memory, update, and training-budget constraints of online network control. This paper investigates whether compact quantum-inspired recurrent models can provide effective TM forecasts without relying on dedicated graph, transformer, or diffusion modules. We adapt gated quantum-inspired Kolmogorov-Arnold network fast-weight programmers (QKAN-FWPs) to direct multi-step Abilene TM forecasting, where each model predicts the next 20 five-minute frames of a 144-channel origin-destination (OD) matrix from a two-hour history. We benchmark three QKAN placement variants against a matched-size long short-term memory (LSTM) network, a larger LSTM, and a classical gated fast-weight programmer under a shared fixed-budget training protocol. Among the evaluated recurrent models, G-QKANFWP achieves the best pooled root-mean-square error (RMSE), while using only 22.4% of the larger LSTM. It also outperforms both the matched-size LSTM and the classical G-FWP baseline, indicating that the gain is not due to gated fast-weight framework alone. Convergence and channel-wise analyses further show that the quantum-inspired variants obtain lower validation-loss area under the learning curve (AULC) than matched-size recurrent baselines, while G-QKANFWP and GQKAN-FWP achieve substantially more OD-channel wins. These results identify a classical slow programmer with a quantum-inspired fast programmer as a promising accuracy-efficiency design for resource-conscious network traffic-matrix forecasting.