arXiv subjects

Alexey Melnikov

Publications and source records attributed to Alexey Melnikov.

At least 19 recordsLinked to original sources

arXiv2026

Hybrid Quantum Neural Networks: Theory, Implementations, and Applications

Artificial intelligence has been transformed by deep neural networks, yet the search for new learning architectures continues. Quantum machine learning offers one such direction, and hybrid quantum neural networks, which combine classical neural-network components with quantum information processing units, have emerged as a practical framework for near-term quantum technologies. However, the rapid development of the field across diverse architectures, benchmarks and hardware assumptions makes it difficult to assess the utility of various proposals, identify where genuine advantages may arise, and determine how practitioners can use these models. While recent benchmarks caution that such gains have not yet been demonstrated at scale, theoretical work has identified tasks on which quantum models hold provable advantages, and hybrid approaches have delivered promising results on practical problems using deliberately compact quantum components and substantially fewer trainable parameters. Here, we review hybrid quantum neural networks for the machine-learning and quantum-machine-learning communities. We summarize their main theoretical and methodological foundations, survey some of the most promising architectures developed so far, and examine their implementation challenges and reported performance. By consolidating these perspectives, this review provides a structured view of the state of the field and helps identify promising paths for future research and application-driven development.

quant-ph↗

arXiv2026

Soft-Quantum Algorithms

Quantum operations on pure states can be fully represented by unitary matrices. Variational quantum circuits, also known as quantum neural networks, embed data and trainable parameters into gate-based operations and optimize the parameters via gradient descent. The high cost of training and low fidelity of current quantum devices, however, restricts much of quantum machine learning to classical simulation. For few-qubit problems with large datasets, training the matrix elements directly, as is done with weight matrices in classical neural networks, can be faster than decomposing data and parameters into gates. We propose a method that trains matrices directly while maintaining unitarity through a single regularization term added to the loss function. A second training step, circuit alignment, then recovers a gate-based architecture from the resulting soft-unitary. On a five-qubit supervised classification task with 1000 datapoints, this two-step process produces a trained variational circuit in under four minutes, compared to over two hours for direct circuit training, while achieving lower binary cross-entropy loss. In a second experiment, soft-unitaries are embedded in a hybrid quantum-classical network for a reinforcement learning cartpole task, where the hybrid agent outperforms a purely classical baseline of comparable size.

quant-ph↗

arXiv2026

Shot-based quantum encoding: a data-loading paradigm for quantum neural networks

Efficient data loading remains a bottleneck for near-term quantum machine learning. Existing schemes (angle, amplitude, and basis encoding) either underuse the exponential Hilbert-space capacity or require circuit depths that exceed the coherence budgets of noisy intermediate-scale quantum hardware. We introduce shot-based quantum encoding (SBQE), a data embedding strategy that distributes the hardware's native resource, shots, according to a data-dependent classical distribution over multiple initial quantum states. By treating the shot counts as a learnable degree of freedom, SBQE produces a mixed-state representation whose expectation values are linear in the classical probabilities and can therefore be composed with nonlinear activation functions. We show that SBQE is structurally equivalent to a multilayer perceptron whose weights are realized by quantum circuits, and we describe a hardware-compatible implementation protocol. Benchmarks on three image datasets, with 10 independent initializations per model, show that SBQE achieves 89.1% +- 0.9% test accuracy on Semeion (reducing error by 5.3% relative to amplitude encoding and matching a width-matched classical network), 80.95% +- 0.10% on Fashion MNIST (exceeding amplitude encoding by +2.0% and a linear multilayer perceptron by +1.3%), and 90.25% +- 0.18% on MNIST (exceeding amplitude encoding by 2.1 percentage points and the width-matched classical network by 0.3), all without any data-encoding gates.

quant-ph↗

arXiv2026

Hybrid Fourier Neural Operator for Surrogate Modeling of Laser Processing with a Quantum-Circuit Mixer

Data-driven surrogates can replace expensive multiphysics solvers for parametric PDEs, yet building compact, accurate neural operators for three-dimensional problems remains challenging: in Fourier Neural Operators, dense mode-wise spectral channel mixing scales linearly with the number of retained Fourier modes, inflating parameter counts and limiting real-time deployability. We introduce HQ-LP-FNO, a hybrid quantum-classical FNO that replaces a configurable fraction of these dense spectral blocks with a compact, mode-shared variational quantum circuit mixer whose parameter count is independent of the Fourier mode budget. A parameter-matched classical bottleneck control is co-designed to provide a rigorous evaluation framework. Evaluated on three-dimensional surrogate modeling of high-energy laser processing, coupling heat transfer, melt-pool convection, free-surface deformation, and phase change, HQ-LP-FNO reduces trainable parameters by 15.6% relative to a classical baseline while lowering phase-fraction mean absolute error by 26% and relative temperature MAE from 2.89% to 2.56%. A sweep over the quantum-channel budget reveals that a moderate VQC allocation yields the best temperature metrics across all tested configurations, including the fully classical baseline, pointing toward an optimal classical-quantum partitioning. The ablation confirms that mode-shared mixing, naturally implemented by the VQC through its compact circuit structure, is the dominant contributor to these improvements. A noisy-simulator study under backend-calibrated noise from ibm-torino confirms numerical stability of the quantum mixer across the tested shot range. These results demonstrate that VQC-based parameter-efficient spectral mixing can improve neural operator surrogates for complex multiphysics problems and establish a controlled evaluation protocol for hybrid quantum operator learning in practice.

quant-ph↗

arXiv2026

A Fast and Generalizable Fourier Neural Operator-Based Surrogate for Melt-Pool Prediction in Laser Processing

High-fidelity simulations of laser welding capture complex thermo-fluid phenomena, including phase change, free-surface deformation, and keyhole dynamics, however their computational cost limits large-scale process exploration and real-time use. In this work we present the Laser Processing Fourier Neural Operator (LP-FNO), a Fourier Neural Operator (FNO) based surrogate model that learns the parametric solution operator of various laser processes from multiphysics simulations generated with FLOW-3D WELD (registered trademark). Through a novel approach of reformulating the transient problem in the moving laser frame and applying temporal averaging, the system results in a quasi-steady state setting suitable for operator learning, even in the keyhole welding regime. The proposed LP-FNO maps process parameters to three-dimensional temperature fields and melt-pool boundaries across a broad process window spanning conduction and keyhole regimes using the non-dimensional normalized enthalpy formulation. The model achieves temperature prediction errors on the order of 1% and intersection-over-union scores for melt-pool segmentation over 0.9. We demonstrate that a LP-FNO model trained on coarse-resolution data can be evaluated on finer grids, yielding accurate super-resolved predictions in mesh-converged conduction regimes, whereas discrepancies in keyhole regimes reflect unresolved dynamics in the coarse-mesh training data. These results indicate that the LP-FNO provides an efficient surrogate modeling framework for laser welding, enabling prediction of full three-dimensional fields and phase interfaces over wide parameter ranges in just tens of milliseconds, up to a hundred thousand times faster than traditional Finite Volume multi-physics software.

cs.LG↗

arXiv2025

Milliarcsecond astrometric oscillations in active galactic nuclei as a precursor of multi-messenger gravitational wave events

The existence of supermassive black hole binaries (SMBHBs) is predicted by various cosmological and evolutionary scenarios for active galactic nuclei. These objects are considered as contributors into the gravitational wave (GW) background and emitters of discrete GW bursts. Yet, SMBHBs remain a rather elusive class of extragalactic objects. Previously we have identified the quasar J2102+6015 as potential SMBHB system based on its oscillating astrometric pattern. We analysed the available VLBI astrometry data and identified another case of astrometric oscillations in the source J0204+1514. We assume these oscillations as manifestations of orbital motion in a binary systems. We estimated parameters of the suspected SMBHB in this source and applied basic theoretical models for projecting its evolution toward coalescence. We also develop a toy model of SMBHB consistent with the discovered astrometric oscillations and give quantitative predictions of GW emission of such the source using the case of J0204+1514 as an example. As an ad hoc result, we also provide a re-assessed estimate of the redshift of J2102+6015, z=1.42. A toy model of the object containing SMBHB with parameters consistent with the observed astrometric oscillations of the source J0204+1514 enabled us to consider GW emission as the cause of the system's orbital evolution. Astrometric VLBI monitoring has an appreciable potential for future detections of SMBHBs as multi-messenger targets for both electromagnetic (in radio domain) and gravitational wave astronomy. To outline the contours of a future physical model connecting SMBHB with detectable GW manifestations, we apply the toy model to the source J0204+1514. We also provide justification for aiming future space-borne VLBI missions toward direct imaging of SMBHBs as a synergistic contribution into future multi-messenger studies involving prospective GW facilities.

astro-ph.CO↗

arXiv2025

Superposed parameterised quantum circuits

Quantum machine learning has shown promise for high-dimensional data analysis, yet many existing approaches rely on linear unitary operations and shared trainable parameters across outputs. These constraints limit expressivity and scalability relative to the multi-layered, non-linear architectures of classical deep networks. We introduce superposed parameterised quantum circuits to overcome these limitations. By combining flip-flop quantum random-access memory with repeat-until-success protocols, a superposed parameterised quantum circuit embeds an exponential number of parameterised sub-models in a single circuit and induces polynomial activation functions through amplitude transformations and post-selection. We provide an analytic description of the architecture, showing how multiple parameter sets are trained in parallel while non-linear amplitude transformations broaden representational power beyond conventional quantum kernels. Numerical experiments underscore these advantages: on a 1D step-function regression a two-qubit superposed parameterised quantum circuit cuts the mean-squared error by three orders of magnitude versus a parameter-matched variational baseline; on a 2D star-shaped two-dimensional classification task, introducing a quadratic activation lifts accuracy to 81.4\% and reduces run-to-run variance three-fold. These results position superposed parameterised quantum circuits as a hardware-efficient route toward deeper, more versatile parameterised quantum circuits capable of learning complex decision boundaries.

quant-ph↗

arXiv2025

TQml Simulator: optimized simulation of quantum machine learning

Hardware-efficient circuits employed in Quantum Machine Learning are typically composed of alternating layers of uniformly applied gates. High-speed numerical simulators for such circuits are crucial for advancing research in this field. In this work, we numerically benchmark universal and gate-specific techniques for simulating the action of layers of gates on quantum state vectors, aiming to accelerate the overall simulation of Quantum Machine Learning algorithms. Our analysis shows that the optimal simulation method for a given layer of gates depends on the number of qubits involved, and that a tailored combination of techniques can yield substantial performance gains in the forward and backward passes for a given circuit. Building on these insights, we developed a numerical simulator, named TQml Simulator, that employs the most efficient simulation method for each layer in a given circuit. We evaluated TQml Simulator on circuits constructed from standard gate sets, such as rotations and CNOTs, as well as on native gates from IonQ and IBM quantum processing units. In most cases, our simulator outperforms equivalent Pennylane's default.qubit simulator by up to a factor of 10, depending on the circuit, the number of qubits, the batch size of the input data, and the hardware used.

quant-ph↗

arXiv2025

Hybrid quantum recurrent neural network for remaining useful life prediction of turbofan engines

Accurate remaining useful life (RUL) estimation underpins safe operation and cost-effective maintenance of aerospace propulsion systems. We propose a Hybrid Quantum Recurrent Neural Network (HQRNN) for jet-engine RUL forecasting on the NASA C-MAPSS FD001 benchmark. The HQRNN stacks Quantum Long Short-Term Memory (QLSTM) layers, replacing each LSTM gate's linear transformation with a Quantum Depth-Infused (QDI) circuit; this is followed by classical dense layers. Quantum and hybrid quantum-classical methods for turbofan RUL prediction are still at an early stage. Our study is therefore among the first to evaluate a gate-based QLSTM hybrid at matched parameter counts, comparing it against classical and joint state-of-the-art models on this benchmark and complementing that comparison with a circuit-level analysis of the quantum layer. Encoding the gate signals in a quantum feature space is intended to help the network represent high-frequency degradation patterns with fewer trainable parameters than a matched classical counterpart. The HQRNN improves mean RMSE and mean MAE by about 5% over matched-parameter stacked-LSTM RNNs across 10 random seeds, and attains a test RMSE of 15.46, outperforming Random Forest, CNN, and MLP baselines. ZX calculus, Fisher information, and Fourier analyses indicate that the QDI circuit is compact, trainable, and expressive. Advanced joint deep-learning models still outperform the stand-alone HQRNN, indicating that quantum-enhanced recurrent modules are best deployed as components within composite prognostics pipelines rather than stand-alone predictors.

cs.LG↗

arXiv2025

Predictive control of blast furnace temperature in steelmaking with hybrid depth-infused quantum neural networks

Accurate prediction and stabilization of blast furnace temperatures are crucial for optimizing the efficiency and productivity of steel production. Traditional methods often struggle with the complex and non-linear nature of the temperature fluctuations within blast furnaces. This paper proposes a novel approach that combines hybrid quantum machine learning with pulverized coal injection control to address these challenges. By integrating classical machine learning techniques with quantum computing algorithms, we aim to enhance predictive accuracy and achieve more stable temperature control. For this we utilized a unique prediction-based optimization method. Our method leverages quantum-enhanced feature space exploration and the robustness of classical regression models to forecast temperature variations and optimize pulverized coal injection values. Our results demonstrate a significant improvement in prediction accuracy over 25 percent and our solution improved temperature stability to +-7.6 degrees of target range from the earlier variance of +-50 degrees, highlighting the potential of hybrid quantum machine learning models in industrial steel production applications.

quant-ph↗

arXiv2025

Multi-stream physics hybrid networks for solving Navier-Stokes equations

Understanding and solving fluid dynamics equations efficiently remains a fundamental challenge in computational physics. Traditional numerical solvers and physics-informed neural networks struggle to capture the full range of frequency components in partial differential equation solutions, limiting their accuracy and efficiency. Here, we propose the Multi-stream Physics Hybrid Network, a novel neural architecture that integrates quantum and classical layers in parallel to improve the accuracy of solving fluid dynamics equations, namely ''Kovasznay flow'' problem. This approach decomposes the solution into separate frequency components, each predicted by independent Parallel Hybrid Networks, simplifying the training process and enhancing performance. We evaluated the proposed model against a comparable classical neural network, the Multi-stream Physics Classical Network, in both data-driven and physics-driven scenarios. Our results show that the Multi-stream Physics Hybrid Network achieves a reduction in root mean square error by 36% for velocity components and 41% for pressure prediction compared to the classical model, while using 24% fewer trainable parameters. These findings highlight the potential of hybrid quantum-classical architectures for advancing computational fluid dynamics.

physics.flu-dyn↗

arXiv2025

Tensor networks for quantum computing

In the rapidly evolving field of quantum computing, tensor networks serve as an important tool due to their multifaceted utility. In this paper, we review the diverse applications of tensor networks and show that they are an important instrument for quantum computing. Specifically, we summarize the application of tensor networks in various domains of quantum computing, including simulation of quantum computation, quantum circuit synthesis, quantum error correction and mitigation, and quantum machine learning. Finally, we provide an outlook on the opportunities and the challenges of the tensor-network techniques.

quant-ph↗

arXiv2024

Information plane and compression-gnostic feedback in quantum machine learning

The information plane (Tishby et al. arXiv:physics/0004057, Shwartz-Ziv et al. arXiv:1703.00810) has been proposed as an analytical tool for studying the learning dynamics of neural networks. It provides quantitative insight on how the model approaches the learned state by approximating a minimal sufficient statistics. In this paper we extend this tool to the domain of quantum learning models. In a second step, we study how the insight on how much the model compresses the input data (provided by the information plane) can be used to improve a learning algorithm. Specifically, we consider two ways to do so: via a multiplicative regularization of the loss function, or with a compression-gnostic scheduler of the learning rate (for algorithms based on gradient descent). Both ways turn out to be equivalent in our implementation. Finally, we benchmark the proposed learning algorithms on several classification and regression tasks using variational quantum circuits. The results demonstrate an improvement in test accuracy and convergence speed for both synthetic and real-world datasets. Additionally, with one example we analyzed the impact of the proposed modifications on the performances of neural networks in a classification task.

quant-ph↗

arXiv2024

Method for noise-induced regularization in quantum neural networks

In the current quantum computing paradigm, significant focus is placed on the reduction or mitigation of quantum decoherence. When designing new quantum processing units, the general objective is to reduce the amount of noise qubits are subject to, and in algorithm design, a large effort is underway to provide scalable error correction or mitigation techniques. Yet some previous work has indicated that certain classes of quantum algorithms, such as quantum machine learning, may, in fact, be intrinsically robust to or even benefit from the presence of a small amount of noise. Here, we demonstrate that noise levels in quantum hardware can be effectively tuned to enhance the ability of quantum neural networks to generalize data, acting akin to regularisation in classical neural networks. As an example, we consider two regression tasks, where, by tuning the noise level in the circuit, we demonstrated improvement of the validation mean squared error loss. Moreover, we demonstrate the method's effectiveness by numerically simulating quantum neural network training on a realistic model of a noisy superconducting quantum computer.

quant-ph↗

arXiv2024

Proper motion of the radio jets in two blazars at redshift above 3

There is still a limited number of high-redshift ($z>3$) active galactic nuclei (AGN) whose jet kinematics have been studied with very long baseline interferometry (VLBI). Without a dedicated proper motion survey, regularly conducted astrometric VLBI observations of bright radio-emitting AGN with sensitive arrays can be utilized to follow changes in the jets, by means of high-resolution imaging and brightness distribution modeling. Here we present a first-time VLBI jet kinematic study of NVSS~J080518$+$614423 ($z = 3.033$) and NVSS~J165844$-$073918 ($z = 3.742$), two flat-spectrum radio quasars that display milliarcsecond-scale jet morphology. Archival astrometric observations carried out mainly with the Very Long Baseline Array, supplemented by recent data taken with the European VLBI Network, allowed us to monitor changes in their radio structure in the $7.6-8.6$~GHz frequency band, covering almost two decades. By identifying individual jet components at each epoch, we were able to determine the apparent proper motion for multiple features in both sources. Apparent superluminal motions range between $(1-14)\,c$, and are found to be consistent with studies of other high-redshift AGN targets. Using the physical parameters derived from the brightness distribution modeling, we estimate the Doppler-boosting factors ($\delta \approx 11.2$ and $\delta \approx 2.7$), the Lorentz factors ($\Gamma \approx 7.4$ and $\Gamma \approx 36.6$) and the jet viewing angles ($\theta \approx 4\fdg4$ and $\theta \approx 8\fdg0$), for NVSS~J080518$+$614423 and NVSS~J165844$-$073918, respectively. The data revealed a stationary jet component with negligible apparent proper motion in NVSS~J165844$-$073918.

astro-ph.GA↗

arXiv2023

Hybrid quantum cycle generative adversarial network for small molecule generation

The drug design process currently requires considerable time and resources to develop each new compound that enters the market. This work develops an application of hybrid quantum generative models based on the integration of parametrized quantum circuits into known molecular generative adversarial networks, and proposes quantum cycle architectures that improve model performance and stability during training. Through extensive experimentation on benchmark drug design datasets, QM9 and PC9, the introduced models are shown to outperform the previously achieved scores. Most prominently, the new scores indicate an increase of up to 30% in the quantitative estimation of druglikeness. The new hybrid quantum machine learning algorithms, as well as the achieved scores of pharmacokinetic properties, contribute to the development of fast and accurate drug discovery processes.

q-bio.BM↗

arXiv2023

Photovoltaic power forecasting using quantum machine learning

Accurate forecasting of photovoltaic power is essential for reliable grid integration, yet remains difficult due to highly variable irradiance, complex meteorological drivers, site geography, and device-specific behavior. Although contemporary machine learning has achieved successes, it is not clear that these approaches are optimal: new model classes may further enhance performance and data efficiency. We investigate hybrid quantum neural networks for time-series forecasting of photovoltaic power and introduce two architectures. The first, a Hybrid Quantum Long Short-Term Memory model, reduces mean absolute error and mean squared error by more than 40% relative to the strongest baselines evaluated. The second, a Hybrid Quantum Sequence-to-Sequence model, once trained, it predicts power for arbitrary forecast horizons without requiring prior meteorological inputs and achieves a 16% lower mean absolute error than the best baseline on this task. Both hybrid models maintain superior accuracy when training data are limited, indicating improved data efficiency. These results show that hybrid quantum models address key challenges in photovoltaic power forecasting and offer a practical route to more reliable, data-efficient energy predictions.

cs.LG↗

arXiv2023

Hybrid quantum image classification and federated learning for hepatic steatosis diagnosis

In the realm of liver transplantation, accurately determining hepatic steatosis levels is crucial. Recognizing the essential need for improved diagnostic precision, particularly for optimizing diagnosis time by swiftly handling easy-to-solve cases and allowing the expert time to focus on more complex cases, this study aims to develop cutting-edge algorithms that enhance the classification of liver biopsy images. Additionally, the challenge of maintaining data privacy arises when creating automated algorithmic solutions, as sharing patient data between hospitals is restricted, further complicating the development and validation process. This research tackles diagnostic accuracy by leveraging novel techniques from the rapidly evolving field of quantum machine learning, known for their superior generalization abilities. Concurrently, it addresses privacy concerns through the implementation of privacy-conscious collaborative machine learning with federated learning. We introduce a hybrid quantum neural network model that leverages real-world clinical data to assess non-alcoholic liver steatosis accurately. This model achieves an image classification accuracy of 97%, surpassing traditional methods by 1.8%. Moreover, by employing a federated learning approach that allows data from different clients to be shared while ensuring privacy, we maintain an accuracy rate exceeding 90%. This initiative marks a significant step towards a scalable, collaborative, efficient, and dependable computational framework that aids clinical pathologists in their daily diagnostic tasks.

cs.LG↗