Quantum machine learning for quantum anomaly detection

Abstract

Anomaly detection is used for identifying data that deviate from `normal' data patterns. Its usage on classical data finds diverse applications in many important areas like fraud detection, medical diagnoses, data cleaning and surveillance. With the advent of quantum technologies, anomaly detection of quantum data, in the form of quantum states, may become an important component of quantum applications. Machine learning algorithms are playing pivotal roles in anomaly detection using classical data. Two widely-used algorithms are kernel principal component analysis and one-class support vector machine. We find corresponding quantum algorithms to detect anomalies in quantum states. We show that these two quantum algorithms can be performed using resources logarithmic in the dimensionality of quantum states. For pure quantum states, these resources can also be logarithmic in the number of quantum states used for training the machine learning algorithm. This makes these algorithms potentially applicable to big quantum data applications.

arXiv comment11 pages, 1 figure

References in corpus (19)

• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Quantum support vector machine for big data classification
• Quantum principal component analysis
• Quantum fingerprinting
• Quantum Data Fitting
• Quantum machine learning: a classical perspective
• Quantum-enhanced machine learning
• Prediction by linear regression on a quantum computer
• Optimal quantum learning of a unitary transformation
• Quantum circuits cannot control unknown operations
• Quantum learning and universal quantum matching machine
• An alternative quantum fidelity for mixed states of qudits
• Quantum Template Matching
• Quantum change point
• Inductive supervised quantum learning
• The Learnability of Quantum States
• Experimentally feasible measures of distance between quantum operations
• Anomaly detection in reconstructed quantum states using a machine-learning technique

Cited by in corpus (51)

• Solving nonlinear differential equations with differentiable quantum circuits
• Mixed Quantum-Classical Method For Fraud Detection with Quantum Feature Selection
• Quantum Machine Learning in High Energy Physics
• Quantum data compression by principal component analysis
• Vulnerability of quantum classification to adversarial perturbations
• Automatic design of quantum feature maps
• Beyond the swap test: optimal estimation of quantum state overlap
• Anomaly detection with variational quantum generative adversarial networks
• Detecting quantum entanglement with unsupervised learning
• Quantum algorithm for visual tracking
• Quantum classification of the MNIST dataset with Slow Feature Analysis
• Quantum machine learning and quantum biomimetics: A perspective
• Quantum Anomaly Detection with Density Estimation and Multivariate Gaussian Distribution
• Resonant Quantum Principal Component Analysis
• Quantum Embedding Search for Quantum Machine Learning
• Variational Quantum Algorithms for Dimensionality Reduction and Classification
• Improved quantum algorithm for A-optimal projection
• Variational Quantum Anomaly Detection: Unsupervised mapping of phase diagrams on a physical quantum computer
• Quantum algorithms for anomaly detection using amplitude estimation
• Exponential data encoding for quantum supervised learning
• Unsupervised classification of quantum data
• Variational quantum one-class classifier
• Quantum algorithm for Neighborhood Preserving Embedding
• A duplication-free quantum neural network for universal approximation
• Optimal Usage of Quantum Random Access Memory in Quantum Machine Learning
• Modular Quantum Computation in a Trapped Ion System
• Networked Quantum Services
• Quantum algorithms for the generalized eigenvalue problem
• Quantum Advantage Seeker with Kernels (QuASK): a software framework to speed up the research in quantum machine learning
• Experimental implementation of quantum algorithm for association rules mining
• Detecting Violations of Differential Privacy for Quantum Algorithms
• Quantum Algorithm for Unsupervised Anomaly Detection
• Experimental demonstration of quantum learning speed-up with classical input data
• Photonic kernel machine learning for ultrafast spectral analysis
• Quantum support vector data description for anomaly detection
• Identification of malfunctioning quantum devices
• Quantum algorithms for matrix geometric means
• Optimal quantum discrimination of single-qubit unitary gates between two candidates
• Quantum State Discrimination for Supervised Classification
• Quantum density estimation with density matrices: Application to quantum anomaly detection
• Quantum secure learning with classical samples
• Quantum Edge Detection
• Evidence of Ferromagnetic Clusters and Griffiths Singularity in Magnetic Weyl Semimetal Co${}_3$Sn${}_2$S${}_2$
• Quadratic Quantum Speedup for Perceptron Training
• Quantum multi-anomaly detection
• Reproducing kernel Hilbert C*-module and kernel mean embeddings
• Quantum Anomaly Detection with a Spin Processor in Diamond
• Batched quantum state exponentiation and quantum Hebbian learning
• Ensuring superior learning outcomes and data security for authorized learner
• Kernel Mean Embeddings of Von Neumann-Algebra-Valued Measures
• Multiclass Portfolio Optimization via Variational Quantum Eigensolver with Dicke State Ansatz