Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2601.10801

Towards Tensor Network Models for Low-Latency Jet Tagging on FPGAs

Alberto Coppi, Ema Puljak, Lorenzo Borella, Daniel Jaschke, Enrique Rico, Maurizio Pierini, Jacopo Pazzini, Andrea Triossi, Simone Montangero

cs.LGhep-exphysics.ins-detquant-phSubmitted Jan 15, 2026• Announced Jan 19, 2026
arXivHTMLPDF

Abstract

We present a systematic study of Tensor Network (TN) models $\unicode{x2013}$ Matrix Product States (MPS) and Tree Tensor Networks (TTN) $\unicode{x2013}$ for real-time jet tagging in high-energy physics, with a focus on low-latency deployment on Field Programmable Gate Arrays (FPGAs). Motivated by the strict requirements of the HL-LHC Level-1 trigger system, we explore TNs as compact and interpretable alternatives to deep neural networks. Using low-level jet constituent features, our models achieve competitive performance compared to state-of-the-art deep learning classifiers. We investigate post-training quantization to enable hardware-efficient implementations without degrading classification performance or latency. The best-performing models are synthesized to estimate FPGA resource usage, latency, and memory occupancy, demonstrating sub-microsecond latency and supporting the feasibility of online deployment in real-time trigger systems. Overall, this study highlights the potential of TN-based models for fast and resource-efficient inference in low-latency environments.

Comments
10 pages, 8 figures

Related papers

Ultra-low latency quantum-inspired machine learning predictors implemented on FPGA

Lorenzo Borella, Alberto Coppi, Andrea Triossi +4 more

Abstract Tensor networks (TNs) are a computational paradigm used for representing quantum many-body systems. Recent works have shown how TNs can also be applied to perform machine learning (ML) tasks, yielding comparable results to standard supervised learning techniques. In this work, we study the use of Tree TNs (TTNs) in high-frequency real-time applications by exploiting the low-latency hardware of the field-programmable gate array (FPGA) technology. We present different implementations of TTN classifiers, capable of performing inference on classical ML datasets as well as on complex physics data. A preparatory analysis of bond dimensions and weight quantization is realized in the training phase, together with entanglement entropy and correlation measurements, that help setting the choice of the TTN architecture. The generated TTNs are then deployed on a hardware accelerator; using an FPGA integrated into a server, the inference of the TTN is completely offloaded. Eventually, a classifier for high energy physics applications is implemented and executed fully pipelined with sub-microsecond latency.

arXiv:2409.16075•Machine Learning Science and Technology•Dec 10, 2025•15 citations

Tree Tensor Network implemented on FPGA as ultra-low latency binary classifiers.

Lorenzo Borella, Alberto Coppi, J. Pazzini +3 more

Tensor Networks (TNs) are a computational framework traditionally used to model quantum many-body systems. Recent research has demonstrated that TNs can also be effectively applied to Machine Learning (ML) tasks, producing results comparable to conventional supervised learning methods. In this work, we investigate the use of Tree Tensor Networks (TTNs) for high-frequency real-time applications by harnessing the low-latency capabilities of Field-Programmable Gate Arrays (FPGAs). We present the implementation of TTN classifiers on FPGA hardware, optimized for performing inference on classical ML benchmarking datasets. Various degrees of parallelization are explored to evaluate the trade-offs between resource utilization and algorithm latency. By deploying these TTNs on a hardware accelerator and utilizing an FPGA integrated into a server, we fully offload the TTN inference process, demonstrating the system’s viability for real-time ML applications.

International Conference on High Energy Physics (ICHEP)•Jan 27, 2025•0 citations

QTN-Hybrid: A DSP-Free Non-Linear Tensor-Network Classifier for Low-Latency FPGA Inference

Kyung-Won Cho, Sunghyun Go, Sungkwan Youm

Tensor-network (TN) classifiers based on matrix-product states (MPS) have recently emerged as a route to fully DSP-free inference on FPGAs, but to the best of our knowledge, every reported deployment has been strictly multilinear. We address this gap by introducing QTN-Hybrid, a quantum-inspired tensor-network (QTN) hybrid design in which a DSP-free non-linear MPS classifier inserts a LUT-fabric-mapped Hardtanh activation (implemented as two signed comparators and a three-way selection multiplexer) between bond contractions. The Hardtanh non-linearity bounds the hidden vector after every bond contraction and thereby confines the fixed-point dynamic range along the chain, so that accuracy is retained at low precision while hardware resources are reduced at the same time. The proposed model is trained on Fashion-MNIST at an operating point comparable in size to the published cascaded spaced-matrix-product-operator (CSMPO) reference design ( $\chi =4$ , thirty-two sites, $\approx 1{\,}$ k parameters), repeated over five random seeds, and evaluated after post-training quantization at precisions from 4–16 bits. At every precision QTN-Hybrid is more accurate than the linear MPS, by + 4.38–4.50 pp at 8–16 bits and by + 5.30 pp at 6 bits, and at 6 bits it remains above the 16-bit linear baseline. On the hardware side, the kernels are C-synthesised by high-level synthesis at a $250{\,}$ MHz target clock and the generated RTL is logic-synthesised to obtain resource and timing figures. The resulting designs use zero DSP blocks and require several times fewer LUTs than the linear 16-bit baseline, and both the 8-bit and the 6-bit configurations pass post-synthesis resource-capacity and timing checks on a mid-range FPGA and on a low-cost edge system-on-module, indicating at the post-synthesis level that deployment on small FPGAs is feasible, while routability and on-board operation remain to be verified.

IEEE Access•Jan 1, 2026•0 citations

Hardware-Aware Tensor Networks for Real-Time Quantum-Inspired Anomaly Detection at Particle Colliders

S. V. Addepalli, P. Bhattarai, Abhilasha Dave +1 more

Quantum machine learning offers the ability to capture complex correlations in high-dimensional feature spaces, crucial for the challenge of detecting beyond the Standard Model physics in collider events, along with the potential for unprecedented computational efficiency in future quantum processors. Near-term utilization of these benefits can be achieved by developing quantum-inspired algorithms for deployment in classical hardware to enable applications at the "edge" of current scientific experiments. This work demonstrates the use of tensor networks for real-time anomaly detection in collider detectors. A spaced matrix product operator (SMPO) is developed that provides sensitivity to a variety beyond the Standard Model benchmarks, and can be implemented in field programmable gate array hardware with resources and latency consistent with trigger deployment. The cascaded SMPO architecture is introduced as an SMPO variation that affords greater flexibility and efficiency in ways that are key to edge applications in resource-constrained environments. These results reveal the benefit and near-term feasibility of deploying quantum-inspired ML in high energy colliders.

arXiv:2603.26604•Mar 27, 2026•2 citations

Quantum-inspired machine learning on high-energy physics data

Timo Felser, Marco Trenti, L. Sestini +4 more

Abstract Tensor Networks, a numerical tool originally designed for simulating quantum many-body systems, have recently been applied to solve Machine Learning problems. Exploiting a tree tensor network, we apply a quantum-inspired machine learning technique to a very important and challenging big data problem in high-energy physics: the analysis and classification of data produced by the Large Hadron Collider at CERN. In particular, we present how to effectively classify so-called b-jets, jets originating from b-quarks from proton–proton collisions in the LHCb experiment, and how to interpret the classification results. We exploit the Tensor Network approach to select important features and adapt the network geometry based on information acquired in the learning process. Finally, we show how to adapt the tree tensor network to achieve optimal precision or fast response in time without the need of repeating the learning process. These results pave the way to the implementation of high-frequency real-time applications, a key ingredient needed among others for current and future LHCb event classification able to trigger events at the tens of MHz scale.

arXiv:2004.13747•npj Quantum Information•Jul 15, 2021•75 citations

Lund Plane to Bloch (LP2B) Encoding for Object and Polarization Tagging with Quantum Jet Substructure

Fabrizio Napolitano, Luca Della Penna, Tommaso Tedeschi +1 more

The application of quantum algorithms to jet substructure analysis is of growing interest as NISQ hardware continues to mature in qubit count and gate depth. Jet substructure remains essential for addressing demanding and complementary challenges at the LHC and beyond, notably object classification and polarization tagging. However, existing quantum machine learning approaches typically rely on data representations that suffer from infrared and collinear unsafety, sensitivity to non-perturbative effects, or poor scalability. In this work, we introduce the Lund Plane to Bloch (LP2B) encoding, designed to map a theoretically clean and robust representation of jet kinematics directly into qubit states. Leveraging this encoding, we implement a Quantum Tree-Topology Network (QTTN) that natively embeds the hierarchical structure of the Lund tree. We evaluate the QTTN across multiple benchmarks and observe that it matches the performance of large classical deep learning architectures, such as LundNet, on polarization tagging, while maintaining competitive accuracy for W boson and top quark tagging. The architecture demonstrates enhanced sensitivity compared to standard 1P1Q encodings on both polarization and W tagging, and pushes the Pareto front when compared against MLP of similar size and BDTs. Remarkably, the QTTN requires three orders of magnitude fewer parameters than LundNet, demonstrating promises for low-latency FPGA implementations in trigger systems. Furthermore, the QTTN outperforms classical methods in the low-data regime, making it suitable for low-yield, data-driven analyses. We also find that the quantum model is less susceptible to overfitting generator-specific parton shower and hadronization models than classical deep learning approaches, pointing toward potentially smaller systematic uncertainties. We validate the QTTN on real quantum hardware using a 3-qubit SpinQ device.

quant-pharXiv:2604.18613•The European Physical Journal C•Apr 16, 2026•1 citation
We present a systematic study of Tensor Network (TN) models \unicodex2013\unicode{x2013}\unicodex2013 Matrix Product States (MPS) and Tree Tensor Networks (TTN) \unicodex2013\unicode{x2013}\unicodex2013 for real-time jet tagging in high-energy physics, with a focus on low-latency deployment on Field Programmable Gate Arrays (FPGAs). Motivated by the strict requirements of the HL-LHC Level-1 trigger system, we explore TNs as compact and interpretable alternatives to deep neural networks. Using low-level jet constituent features, our models achieve competitive performance compared to state-of-the-art deep learning classifiers. We investigate post-training quantization to enable hardware-efficient implementations without degrading classification performance or latency. The best-performing models are synthesized to estimate FPGA resource usage, latency, and memory occupancy, demonstrating sub-microsecond latency and supporting the feasibility of online deployment in real-time trigger systems. Overall, this study highlights the potential of TN-based models for fast and resource-efficient inference in low-latency environments.
Abstract Tensor networks (TNs) are a computational paradigm used for representing quantum many-body systems. Recent works have shown how TNs can also be applied to perform machine learning (ML) tasks, yielding comparable results to standard supervised learning techniques. In this work, we study the use of Tree TNs (TTNs) in high-frequency real-time applications by exploiting the low-latency hardware of the field-programmable gate array (FPGA) technology. We present different implementations of TTN classifiers, capable of performing inference on classical ML datasets as well as on complex physics data. A preparatory analysis of bond dimensions and weight quantization is realized in the training phase, together with entanglement entropy and correlation measurements, that help setting the choice of the TTN architecture. The generated TTNs are then deployed on a hardware accelerator; using an FPGA integrated into a server, the inference of the TTN is completely offloaded. Eventually, a classifier for high energy physics applications is implemented and executed fully pipelined with sub-microsecond latency.
Tensor Networks (TNs) are a computational framework traditionally used to model quantum many-body systems. Recent research has demonstrated that TNs can also be effectively applied to Machine Learning (ML) tasks, producing results comparable to conventional supervised learning methods. In this work, we investigate the use of Tree Tensor Networks (TTNs) for high-frequency real-time applications by harnessing the low-latency capabilities of Field-Programmable Gate Arrays (FPGAs). We present the implementation of TTN classifiers on FPGA hardware, optimized for performing inference on classical ML benchmarking datasets. Various degrees of parallelization are explored to evaluate the trade-offs between resource utilization and algorithm latency. By deploying these TTNs on a hardware accelerator and utilizing an FPGA integrated into a server, we fully offload the TTN inference process, demonstrating the system’s viability for real-time ML applications.
Tensor-network (TN) classifiers based on matrix-product states (MPS) have recently emerged as a route to fully DSP-free inference on FPGAs, but to the best of our knowledge, every reported deployment has been strictly multilinear. We address this gap by introducing QTN-Hybrid, a quantum-inspired tensor-network (QTN) hybrid design in which a DSP-free non-linear MPS classifier inserts a LUT-fabric-mapped Hardtanh activation (implemented as two signed comparators and a three-way selection multiplexer) between bond contractions. The Hardtanh non-linearity bounds the hidden vector after every bond contraction and thereby confines the fixed-point dynamic range along the chain, so that accuracy is retained at low precision while hardware resources are reduced at the same time. The proposed model is trained on Fashion-MNIST at an operating point comparable in size to the published cascaded spaced-matrix-product-operator (CSMPO) reference design ( χ=4\chi =4χ=4 , thirty-two sites, ≈1 \approx 1{\,}≈1 k parameters), repeated over five random seeds, and evaluated after post-training quantization at precisions from 4–16 bits. At every precision QTN-Hybrid is more accurate than the linear MPS, by + 4.38–4.50 pp at 8–16 bits and by + 5.30 pp at 6 bits, and at 6 bits it remains above the 16-bit linear baseline. On the hardware side, the kernels are C-synthesised by high-level synthesis at a 250 250{\,}250 MHz target clock and the generated RTL is logic-synthesised to obtain resource and timing figures. The resulting designs use zero DSP blocks and require several times fewer LUTs than the linear 16-bit baseline, and both the 8-bit and the 6-bit configurations pass post-synthesis resource-capacity and timing checks on a mid-range FPGA and on a low-cost edge system-on-module, indicating at the post-synthesis level that deployment on small FPGAs is feasible, while routability and on-board operation remain to be verified.
Quantum machine learning offers the ability to capture complex correlations in high-dimensional feature spaces, crucial for the challenge of detecting beyond the Standard Model physics in collider events, along with the potential for unprecedented computational efficiency in future quantum processors. Near-term utilization of these benefits can be achieved by developing quantum-inspired algorithms for deployment in classical hardware to enable applications at the "edge" of current scientific experiments. This work demonstrates the use of tensor networks for real-time anomaly detection in collider detectors. A spaced matrix product operator (SMPO) is developed that provides sensitivity to a variety beyond the Standard Model benchmarks, and can be implemented in field programmable gate array hardware with resources and latency consistent with trigger deployment. The cascaded SMPO architecture is introduced as an SMPO variation that affords greater flexibility and efficiency in ways that are key to edge applications in resource-constrained environments. These results reveal the benefit and near-term feasibility of deploying quantum-inspired ML in high energy colliders.
Abstract Tensor Networks, a numerical tool originally designed for simulating quantum many-body systems, have recently been applied to solve Machine Learning problems. Exploiting a tree tensor network, we apply a quantum-inspired machine learning technique to a very important and challenging big data problem in high-energy physics: the analysis and classification of data produced by the Large Hadron Collider at CERN. In particular, we present how to effectively classify so-called b-jets, jets originating from b-quarks from proton–proton collisions in the LHCb experiment, and how to interpret the classification results. We exploit the Tensor Network approach to select important features and adapt the network geometry based on information acquired in the learning process. Finally, we show how to adapt the tree tensor network to achieve optimal precision or fast response in time without the need of repeating the learning process. These results pave the way to the implementation of high-frequency real-time applications, a key ingredient needed among others for current and future LHCb event classification able to trigger events at the tens of MHz scale.
The application of quantum algorithms to jet substructure analysis is of growing interest as NISQ hardware continues to mature in qubit count and gate depth. Jet substructure remains essential for addressing demanding and complementary challenges at the LHC and beyond, notably object classification and polarization tagging. However, existing quantum machine learning approaches typically rely on data representations that suffer from infrared and collinear unsafety, sensitivity to non-perturbative effects, or poor scalability. In this work, we introduce the Lund Plane to Bloch (LP2B) encoding, designed to map a theoretically clean and robust representation of jet kinematics directly into qubit states. Leveraging this encoding, we implement a Quantum Tree-Topology Network (QTTN) that natively embeds the hierarchical structure of the Lund tree. We evaluate the QTTN across multiple benchmarks and observe that it matches the performance of large classical deep learning architectures, such as LundNet, on polarization tagging, while maintaining competitive accuracy for W boson and top quark tagging. The architecture demonstrates enhanced sensitivity compared to standard 1P1Q encodings on both polarization and W tagging, and pushes the Pareto front when compared against MLP of similar size and BDTs. Remarkably, the QTTN requires three orders of magnitude fewer parameters than LundNet, demonstrating promises for low-latency FPGA implementations in trigger systems. Furthermore, the QTTN outperforms classical methods in the low-data regime, making it suitable for low-yield, data-driven analyses. We also find that the quantum model is less susceptible to overfitting generator-specific parton shower and hadronization models than classical deep learning approaches, pointing toward potentially smaller systematic uncertainties. We validate the QTTN on real quantum hardware using a 3-qubit SpinQ device.