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

A Unified Classification Framework with Quantum Metric Learning

Nhat A. Nghiem, Samuel Yen-Chi Chen, Tzu-Chieh Wei

Published Oct 25, 2020• 6 citations
OpenAlex

Abstract

Recently, Lloyd et al. [arXiv:2001.03622] introduced \textit{quantum metric learning} as a powerful framework for quantum supervised learning. Such strategy focuses on the training of the quantum embedding, with a goal of `well-separation' of the embedded data in the Hilbert space $\mathcal{H}$. Motivated by such an idea, we present a metric-based framework for supervised learning with trainable quantum circuits. We introduce both explicit and implicit approaches, based on the \textit{metric} defined on the Hilbert space $\mathcal{H}$, to classify data. In particular, with the implicit approach, the number of separated classes (or their labels) in supervised learning problems can be arbitrarily high (with respect to the number of given qubits, or more precisely, the number of measurement), which is an improvement over current quantum supervised learning models, and this approach requires relatively small number of training points. With the explicit approach, we establish an equivalence between our metric-based framework and other quantum supervised learning models. Such equivalence provides a unification of supervised learning frameworks on quantum computer. We also demonstrate our framework by performing both noise-free and noisy numerical simulations and by running the classification on real IBM Q devices.

Related papers

Unified framework for quantum classification

Nhat A. Nghiem, Samuel Yen-Chi Chen, Tzu-Chieh Wei

Quantum machine learning is an emerging field that combines machine learning with advances in quantum technologies. Many works have suggested great possibilities of using near-term quantum hardware in supervised learning. Motivated by these developments, we present an embedding-based framework for supervised learning with trainable quantum circuits. We introduce both explicit and implicit approaches. The aim of these approaches is to map data from different classes to separated locations in the Hilbert space via a parametrized quantum circuit. We will show that the implicit approach is a generalization of a recently introduced strategy, so-called quantum metric learning. Furthermore, we discuss an intrinsic connection between the explicit approach and those previously proposed quantum classification models. The implicit and explicit approaches, together, provide a unified framework for quantum classification. The utility of our framework is demonstrated by our noise-free and noisy numerical simulations. Moreover, we have conducted classification testing with both implicit and explicit approaches using several IBM Q devices.

arXiv:2010.13186•Physical Review Research•Jul 16, 2021•27 citations

Quantum embeddings for machine learning

Seth Lloyd, Maria Schuld, Aroosa Ijaz +2 more

Quantum classifiers are trainable quantum circuits used as machine learning models. The first part of the circuit implements a quantum feature map that encodes classical inputs into quantum states, embedding the data in a high-dimensional Hilbert space; the second part of the circuit executes a quantum measurement interpreted as the output of the model. Usually, the measurement is trained to distinguish quantum-embedded data. We propose to instead train the first part of the circuit -- the embedding -- with the objective of maximally separating data classes in Hilbert space, a strategy we call quantum metric learning. As a result, the measurement minimizing a linear classification loss is already known and depends on the metric used: for embeddings separating data using the l1 or trace distance, this is the Helstrom measurement, while for the l2 or Hilbert-Schmidt distance, it is a simple overlap measurement. This approach provides a powerful analytic framework for quantum machine learning and eliminates a major component in current models, freeing up more precious resources to best leverage the capabilities of near-term quantum information processors.

arXiv:2001.03622•Jan 10, 2020•198 citations

Invited: Trainable Discrete Feature Embeddings for Quantum Machine Learning

Napat Thumwanit, Chayaphol Lortaraprasert, Rudy Raymond

Quantum classifiers provide sophisticated embeddings of input data in Hilbert space promising quantum advantage. The advantage stems from quantum feature maps encoding the inputs into quantum states with variational quantum circuits. A recent work shows how to map discrete features with fewer quantum bits using Quantum Random Access Coding (QRAC) to encode binary strings into quantum states. We propose a new method to embed discrete features with trainable quantum circuits by combining QRAC and a recently proposed strategy for training quantum feature map called quantum metric learning. The proposed trainable embedding requires not only as few qubits as QRAC but also overcomes the limitations of QRAC to classify inputs whose classes are based on hard Boolean functions. We numerically demonstrate its use in variational quantum classifiers to achieve better performances to classify real-world datasets, and thus its possibility to use near-term quantum computers for machine learning.

ACM/IEEE Design Automation Conference (DAC)•Nov 8, 2021•11 citations

Quantum Metric Learning for New Physics Searches at the LHC

Ahmed Hammad, Kyoungchul Kong, Myeonghun Park +1 more

In the NISQ (Noisy intermediate-scale quantum) area, Quantum computers can be utilized for deep learning by treating variational quantum circuits as neural network models. This can be achieved by first encoding the input data onto quantum computers using nonparametric unitary gates. An alternative approach is to train the data encoding to map input data from different classes to separated locations in the Hilbert space. The separation is achieved with metric loss functions, hence the naming ``Quantum Metric Learning". With the limited number of qubits in the NISQ area, this approach works naturally as a hybrid classical-quantum computation enabling embedding of high-dimensional feature data into a small number of qubits. Here, we consider an example of the global QCD color structure of hard b-jets emerging from color singlet scalar decays to optimize the signal to background discrimination with a hybrid classical-quantum metric learning. Due to the sparsity of data, self-supervised methods with data augmentation have been utilized so far. Compared to the this classical self-supervised approach, our hybrid method shows the better classification performance without data augmentations. We emphasize that performance enhancements independent of data augmentation techniques are devoid of the artificial risks introduced by data augmentation.

arXiv:2311.16866•Nov 28, 2023•1 citation

Supervised Learning with Quantum Hamiltonian Embeddings

Riccardo Molteni, Minjun Jeon, Paolo Braccia +8 more

Machine learning is widely regarded as a promising application in which quantum computing could offer a computational advantage. However, general quantum machine learning models with provable guarantees on performance, trainability, and efficient inference remain limited. In this work, we introduce quantum Hamiltonian embeddings, a supervised learning framework in which a classical training dataset is encoded into a single effective, parameterized Hamiltonian. Training optimizes the parameters of this data-dependent Hamiltonian, whose approximate ground state defines the classification rule. Once the ground state has been approximated using a quantum algorithm, inference can be performed either classically using a classical representation of the learned state, or with a quantum representation of the state. We establish efficient methods for gradient estimation and prove favorable generalization guarantees. Furthermore, under standard cryptographic assumptions, we show that Hamiltonian embeddings can realize hypothesis functions beyond the reach of efficient classical algorithms. We then demonstrate the framework at scale on IBM Heron processors using a standard benchmark dataset. Together, these results establish Hamiltonian embeddings as a new framework for quantum machine learning, combining theoretical guarantees with a path for experimental investigations at scale on quantum hardware.

quant-pharXiv:2610.26833•Oct 20, 2026•0 citations

Generalization Performance of Quantum Metric Learning Classifiers

Jonathan Kim, Stefan Bekiranov

Quantum computing holds great promise for a number of fields including biology and medicine. A major application in which quantum computers could yield advantage is machine learning, especially kernel-based approaches. A recent method termed quantum metric learning, in which a quantum embedding which maximally separates data into classes is learned, was able to perfectly separate ant and bee image training data. The separation is achieved with an intrinsically quantum objective function and the overall approach was shown to work naturally as a hybrid classical-quantum computation enabling embedding of high dimensional feature data into a small number of qubits. However, the ability of the trained classifier to predict test sample data was never assessed. We assessed the performance of quantum metric learning on test ants and bees image data as well as breast cancer clinical data. We applied the original approach as well as variants in which we performed principal component analysis (PCA) on the feature data to reduce its dimensionality for quantum embedding, thereby limiting the number of model parameters. If the degree of dimensionality reduction was limited and the number of model parameters was constrained to be far less than the number of training samples, we found that quantum metric learning was able to accurately classify test data.

Biomolecules•Oct 27, 2022•3 citations
Recently, Lloyd et al. [arXiv:2001.03622] introduced \textit{quantum metric learning} as a powerful framework for quantum supervised learning. Such strategy focuses on the training of the quantum embedding, with a goal of `well-separation' of the embedded data in the Hilbert space H\mathcal{H}H. Motivated by such an idea, we present a metric-based framework for supervised learning with trainable quantum circuits. We introduce both explicit and implicit approaches, based on the \textit{metric} defined on the Hilbert space H\mathcal{H}H, to classify data. In particular, with the implicit approach, the number of separated classes (or their labels) in supervised learning problems can be arbitrarily high (with respect to the number of given qubits, or more precisely, the number of measurement), which is an improvement over current quantum supervised learning models, and this approach requires relatively small number of training points. With the explicit approach, we establish an equivalence between our metric-based framework and other quantum supervised learning models. Such equivalence provides a unification of supervised learning frameworks on quantum computer. We also demonstrate our framework by performing both noise-free and noisy numerical simulations and by running the classification on real IBM Q devices.
Quantum machine learning is an emerging field that combines machine learning with advances in quantum technologies. Many works have suggested great possibilities of using near-term quantum hardware in supervised learning. Motivated by these developments, we present an embedding-based framework for supervised learning with trainable quantum circuits. We introduce both explicit and implicit approaches. The aim of these approaches is to map data from different classes to separated locations in the Hilbert space via a parametrized quantum circuit. We will show that the implicit approach is a generalization of a recently introduced strategy, so-called quantum metric learning. Furthermore, we discuss an intrinsic connection between the explicit approach and those previously proposed quantum classification models. The implicit and explicit approaches, together, provide a unified framework for quantum classification. The utility of our framework is demonstrated by our noise-free and noisy numerical simulations. Moreover, we have conducted classification testing with both implicit and explicit approaches using several IBM Q devices.
Quantum classifiers are trainable quantum circuits used as machine learning models. The first part of the circuit implements a quantum feature map that encodes classical inputs into quantum states, embedding the data in a high-dimensional Hilbert space; the second part of the circuit executes a quantum measurement interpreted as the output of the model. Usually, the measurement is trained to distinguish quantum-embedded data. We propose to instead train the first part of the circuit -- the embedding -- with the objective of maximally separating data classes in Hilbert space, a strategy we call quantum metric learning. As a result, the measurement minimizing a linear classification loss is already known and depends on the metric used: for embeddings separating data using the l1 or trace distance, this is the Helstrom measurement, while for the l2 or Hilbert-Schmidt distance, it is a simple overlap measurement. This approach provides a powerful analytic framework for quantum machine learning and eliminates a major component in current models, freeing up more precious resources to best leverage the capabilities of near-term quantum information processors.
Quantum classifiers provide sophisticated embeddings of input data in Hilbert space promising quantum advantage. The advantage stems from quantum feature maps encoding the inputs into quantum states with variational quantum circuits. A recent work shows how to map discrete features with fewer quantum bits using Quantum Random Access Coding (QRAC) to encode binary strings into quantum states. We propose a new method to embed discrete features with trainable quantum circuits by combining QRAC and a recently proposed strategy for training quantum feature map called quantum metric learning. The proposed trainable embedding requires not only as few qubits as QRAC but also overcomes the limitations of QRAC to classify inputs whose classes are based on hard Boolean functions. We numerically demonstrate its use in variational quantum classifiers to achieve better performances to classify real-world datasets, and thus its possibility to use near-term quantum computers for machine learning.
In the NISQ (Noisy intermediate-scale quantum) area, Quantum computers can be utilized for deep learning by treating variational quantum circuits as neural network models. This can be achieved by first encoding the input data onto quantum computers using nonparametric unitary gates. An alternative approach is to train the data encoding to map input data from different classes to separated locations in the Hilbert space. The separation is achieved with metric loss functions, hence the naming ``Quantum Metric Learning". With the limited number of qubits in the NISQ area, this approach works naturally as a hybrid classical-quantum computation enabling embedding of high-dimensional feature data into a small number of qubits. Here, we consider an example of the global QCD color structure of hard b-jets emerging from color singlet scalar decays to optimize the signal to background discrimination with a hybrid classical-quantum metric learning. Due to the sparsity of data, self-supervised methods with data augmentation have been utilized so far. Compared to the this classical self-supervised approach, our hybrid method shows the better classification performance without data augmentations. We emphasize that performance enhancements independent of data augmentation techniques are devoid of the artificial risks introduced by data augmentation.
Machine learning is widely regarded as a promising application in which quantum computing could offer a computational advantage. However, general quantum machine learning models with provable guarantees on performance, trainability, and efficient inference remain limited. In this work, we introduce quantum Hamiltonian embeddings, a supervised learning framework in which a classical training dataset is encoded into a single effective, parameterized Hamiltonian. Training optimizes the parameters of this data-dependent Hamiltonian, whose approximate ground state defines the classification rule. Once the ground state has been approximated using a quantum algorithm, inference can be performed either classically using a classical representation of the learned state, or with a quantum representation of the state. We establish efficient methods for gradient estimation and prove favorable generalization guarantees. Furthermore, under standard cryptographic assumptions, we show that Hamiltonian embeddings can realize hypothesis functions beyond the reach of efficient classical algorithms. We then demonstrate the framework at scale on IBM Heron processors using a standard benchmark dataset. Together, these results establish Hamiltonian embeddings as a new framework for quantum machine learning, combining theoretical guarantees with a path for experimental investigations at scale on quantum hardware.
Quantum computing holds great promise for a number of fields including biology and medicine. A major application in which quantum computers could yield advantage is machine learning, especially kernel-based approaches. A recent method termed quantum metric learning, in which a quantum embedding which maximally separates data into classes is learned, was able to perfectly separate ant and bee image training data. The separation is achieved with an intrinsically quantum objective function and the overall approach was shown to work naturally as a hybrid classical-quantum computation enabling embedding of high dimensional feature data into a small number of qubits. However, the ability of the trained classifier to predict test sample data was never assessed. We assessed the performance of quantum metric learning on test ants and bees image data as well as breast cancer clinical data. We applied the original approach as well as variants in which we performed principal component analysis (PCA) on the feature data to reduce its dimensionality for quantum embedding, thereby limiting the number of model parameters. If the degree of dimensionality reduction was limited and the number of model parameters was constrained to be far less than the number of training samples, we found that quantum metric learning was able to accurately classify test data.