REVIEW 18 cited by
Quantum embeddings for machine learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 18 Pith papers
-
High-rate qLDPC processors
Non-abelian "mitten" qLDPC codes achieve 20% encoding rate with distances 10-24 on 150-975 qubits, and simulations indicate fault-tolerant processors sustaining ~10^10 logical operations at 0.1% physical error rate.
-
Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support
Quantum Spectral Models encode each matrix input as a Hamiltonian, letting sample-dependent spectral gaps act as tunable Fourier carriers, and lead mean test accuracy on four benchmarks at depth 32.
-
Quantum feature-map learning with reduced resource overhead
By classically reconstructing quantum model outputs, Q-FLAIR selects gates, features, and weights with O(M) quantum evaluations per iteration, decoupling quantum cost from feature dimension and enabling >90% MNIST acc...
-
Fourier Fingerprints of Ansatzes in Quantum Machine Learning
Variational quantum circuits' Fourier coefficients are correlated in ansatz-specific ways, and the new Fourier coefficient correlation metric predicts their training performance better than expressibility in the tested cases.
-
QuKAN: A Quantum Circuit Born Machine approach to Quantum Kolmogorov Arnold Networks
A quantum circuit Born machine can encode B-spline basis functions and trainable coefficients to form hybrid and fully quantum KAN residual functions, demonstrated on toy classification and regression.
-
A Hybrid Quantum Circuit Born Machine Framework for Financial Volatility Forecasting: Quantum-Assisted Training and Classical Inference
LSTM trained with a QCBM generative prior beats a classical LSTM on SSE/CSI 300 realized volatility and retains much of that edge under zero-weight inference via Drop-Prior training.
-
A Multiclass Quantum Aligned Centroid Kernel
A sample-to-centroid fidelity kernel enables linear-scaling multiclass quantum classification; in simulation it beats pure quantum baselines, and untrained 124-qubit hardware results match an RBF kernel.
-
Feature Encoding in Quantum Machine Learning: A Survey and Practical Guidelines
Survey of quantum feature encoding families with a cost-expressivity-robustness taxonomy, closed-form NISQ bounds, and a five-regime decision framework that recommends shallow angle encodings when gate error rate p is...
-
A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
A hybrid quantum-classical temporal graph network with adaptive amplitude encoding claims strong link-prediction results on five TGBL benchmarks, but the evaluation is undermined by a below-random baseline and missing code.
-
HattriQ: Designing Integrated Gradients for Feature Attribution in Quantum Machine Learning
HattriQ computes input-feature attributions for amplitude-encoded quantum classifiers by estimating amplitude gradients with Hadamard-test circuits and integrating them from a baseline image.
-
Hybrid Quantum-Classical Learning for Multiclass Image Classification
A hybrid QCNN that reuses measurements from qubits discarded during pooling reports large accuracy gains on small image benchmarks, but the baseline is not matched in classical capacity.
-
Position: Quantum Kernel Machines Should Move Beyond Scalar-Valued Kernels to Realize Their Potential
The paper proposes a roadmap for quantum operator-valued kernels and shows on simulated quantum channel estimation that they can outperform scalar-valued quantum kernels.
-
Quantum Topological Data Encoding
QTDE encodes higher-order topological structure into quantum states via evolution under the combinatorial Laplacian; on clique-complex benchmarks it edges out a Laplacian-comparison baseline only in easy, high-dimensi...
-
Hybrid Quantum Neural Networks for Efficient Protein-Ligand Binding Affinity Prediction
A hybrid quantum-classical network matches or slightly beats classical baselines on protein-ligand binding affinity prediction while using fewer parameters.
-
Variational Quantum Circuits in Offline Contextual Bandit Problems
Variational quantum circuits can guide particle swarm optimization to find better industrial control configurations in an offline contextual bandit setting, with performance comparable to classical neural networks.
-
Quantum-Classical Hybrid Molecular Autoencoder for Advancing Classical Decoding
A Word2Ket-based quantum autoencoder with an attention LSTM decoder reconstructs SMILES strings, reaching 84% quantum fidelity and 60% Levenshtein similarity on the QM9 training set.
-
Enhanced Quantum behavior on frustrated Ising model: Quantum Approximate Optimization Algorithm study
QAOA simulations of a 4x4 frustrated Ising model show larger deviations from the exact ground state energy near the FM-to-stripe transition, and the paper labels these deviations quantum fluctuations.
-
Adversarial Threats in Quantum Machine Learning: A Survey of Attacks and Defenses
A survey that categorizes known adversarial threats to quantum machine learning systems and reviews existing defenses, from logic locking to hardware-aware watermarking.
Discussion (0). Sign in to comment.