Quantum-enhanced machine learning

Abstract

The emerging field of quantum machine learning has the potential to substantially aid in the problems and scope of artificial intelligence. This is only enhanced by recent successes in the field of classical machine learning. In this work we propose an approach for the systematic treatment of machine learning, from the perspective of quantum information. Our approach is general and covers all three main branches of machine learning: supervised, unsupervised and reinforcement learning. While quantum improvements in supervised and unsupervised learning have been reported, reinforcement learning has received much less attention. Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements. As an example, we show that quadratic improvements in learning efficiency, and exponential improvements in performance over limited time periods, can be obtained for a broad class of learning problems.

5+15 pages. This paper builds upon and mostly supersedes arXiv:1507.08482. In addition to results provided in this previous work, here we achieve learning improvements in more general environments, and provide connections to other work in quantum machine learning. Explicit constructions of oracularized environments given in arXiv:1507.08482 are omitted in this version

References in corpus (11)

• Quantum support vector machine for big data classification
• Quantum random access memory
• The quest for a Quantum Neural Network
• Quantum reinforcement learning
• Automated Search for new Quantum Experiments
• Fixed-point quantum search with an optimal number of queries
• Quantum speedup for active learning agents
• Evolutionary Algorithms for Hard Quantum Control
• Differential Evolution for Many-Particle Adaptive Quantum Metrology
• Adaptive quantum computation in changing environments using projective simulation
• Meta-learning within Projective Simulation

Cited by in corpus (146)

• Quantum Machine Learning
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum Convolutional Neural Networks
• Efficient Learning for Deep Quantum Neural Networks
• Quantum computing for finance: overview and prospects
• Transfer learning in hybrid classical-quantum neural networks
• The Expressive Power of Parameterized Quantum Circuits
• Reinforcement Learning in Different Phases of Quantum Control
• Quantum generalisation of feedforward neural networks
• Implementing a distance-based classifier with a quantum interference circuit
• Is quantum advantage the right goal for quantum machine learning?
• The prospects of quantum computing in computational molecular biology
• Solving nonlinear differential equations with differentiable quantum circuits
• Quantum Hopfield neural network
• Challenges and Opportunities in Quantum Optimization
• Experimental quantum speed-up in reinforcement learning agents
• Quantum reservoir processing
• Quantum generative adversarial network for generating discrete distribution
• Quantum Algorithm for Linear Regression
• Quantum machine learning for quantum anomaly detection
• Hybrid quantum convolutional neural networks model for COVID-19 prediction using chest X-Ray images
• When does reinforcement learning stand out in quantum control? A comparative study on state preparation
• Shortcuts to Adiabaticity in Digitized Adiabatic Quantum Computing
• Quantum Software Engineering: Landscapes and Horizons
• Quantum Neural Network States: A Brief Review of Methods and Applications
• Recent advances for quantum classifiers
• Unitary quantum perceptron as efficient universal approximator
• Biology and medicine in the landscape of quantum advantages
• Basic protocols in quantum reinforcement learning with superconducting circuits
• Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
• Advances in Quantum Reinforcement Learning
• Analytic continuation via domain-knowledge free machine learning
• NISQ Computers: A Path to Quantum Supremacy
• Classification with Quantum Machine Learning: A Survey
• Reconstruction of a Photonic Qubit State with Reinforcement Learning
• Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
• Reconstructing quantum states with quantum reservoir networks
• Measurement-based adaptation protocol with quantum reinforcement learning
• Machine Learning meets Quantum Foundations: A Brief Survey
• Quantum Circuit Cutting with Maximum Likelihood Tomography
• Quantum enhancements for deep reinforcement learning in large spaces
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Markovian Quantum Neuroevolution for Machine Learning
• Quantum Language Model with Entanglement Embedding for Question Answering
• Quantum machine learning and quantum biomimetics: A perspective
• Supervised Quantum Learning without Measurements
• Quantum Embedding Search for Quantum Machine Learning
• Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials
• Projective simulation with generalization
• Machine learning \& artificial intelligence in the quantum domain
• A Projector Quantum Monte Carlo Method for non-linear wavefunctions
• Inductive supervised quantum learning
• Assessing Quantum Computing Performance for Energy Optimization in a Prosumer Community
• Grammar-aware sentence classification on quantum computers
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Quantum Reinforcement Learning: the Maze problem
• Multiqubit and multilevel quantum reinforcement learning with quantum technologies
• New Trends in Quantum Machine Learning
• Policies for elementary links in a quantum network
• Exponential data encoding for quantum supervised learning
• Quantum topology identification with deep neural networks and quantum walks
• Speeding-up the decision making of a learning agent using an ion trap quantum processor
• Quantum Deep Reinforcement Learning for Robot Navigation Tasks
• Efficient Machine Learning Representations of Surface Code with Boundaries, Defects, Domain Walls and Twists
• Unsupervised classification of quantum data
• Experimental quantum pattern recognition in IBMQ and diamond NVs
• Entanglement-guided architectures of machine learning by quantum tensor network
• Machine Learning and Quantum Devices
• Benchmarking projective simulation in navigation problems
• Reinforcement learning for semi-autonomous approximate quantum eigensolver
• Variational Quantum Algorithms for the Allocation of Resources in a Cloud/Edge Architecture
• Enhanced Quantum Synchronization via Quantum Machine Learning
• Explaining Quantum Circuits with Shapley Values: Towards Explainable Quantum Machine Learning
• Entanglement detection with classical deep neural networks
• Entanglement-based quantum deep learning
• Quantum reinforcement learning in continuous action space
• Networked Quantum Services
• Measurement-based adaptation protocol with quantum reinforcement learning in a Rigetti quantum computer
• Protocol for implementing quantum nonparametric learning with trapped ions
• Machine learning effective models for quantum systems
• Quantum-enhanced least-square support vector machine: simplified quantum algorithm and sparse solutions
• Quantum exploration algorithms for multi-armed bandits
• Realizing quantum linear regression with auxiliary qumodes
• Fast optimization of parametrized quantum optical circuits
• Optimizing Counterdiabaticity by Variational Quantum Circuits
• Quantum Bandits
• Quantum adaptive agents with efficient long-term memories
• Benefits of Open Quantum Systems for Quantum Machine Learning
• A hybrid classical-quantum approach to speed-up Q-learning
• On the convergence of projective-simulation-based reinforcement learning in Markov decision processes
• Classical Artificial Neural Network Training Using Quantum Walks as a Search Procedure
• What can we learn from quantum convolutional neural networks?
• On the effects of biased quantum random numbers on the initialization of artificial neural networks
• Quantum kernels with squeezed-state encoding for machine learning
• Quantum Expectation-Maximization Algorithm
• Discriminating Quantum States with Quantum Machine Learning
• Experimental demonstration of quantum learning speed-up with classical input data
• Entanglement-induced provable and robust quantum learning advantages
• A Physical Quantum Agent
• Quantum-accessible reinforcement learning beyond strictly epochal environments
• A quantum collisional classifier driven by information reservoir
• Performance analysis of a hybrid agent for quantum-accessible reinforcement learning
• Parametric Probabilistic Quantum Memory
• Quantum-enhanced learning of rotations about an unknown direction
• Theoretical analysis of a nearly optimal analog quantum search
• Machine-learning based noise characterization and correction on neutral atoms NISQ devices
• QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
• Quantum DeepONet: Neural operators accelerated by quantum computing
• Trapped-Ion Entangling Gates Robust Against Qubit Frequency Errors
• Quantum reinforcement learning in the presence of thermal dissipation
• Application of quantum-inspired generative models to small molecular datasets
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Transition Probabilities in Generalized Quantum Search Hamiltonian Evolutions
• Image Compression and Classification Using Qubits and Quantum Deep Learning
• Rademacher complexity of noisy quantum circuits
• Comparative Analysis of Quantum and Classical Support Vector Classifiers for Software Bug Prediction: An Exploratory Study
• Implementation and Empirical Evaluation of a Quantum Machine Learning Pipeline for Local Classification
• The Roles of Kerr nonlinearity in a Bosonic Quantum Neural Network
• Framework for Learning and Control in the Classical and Quantum Domains
• Quantum optimal control in quantum technologies. Strategic report on current status, visions and goals for research in Europe
• Exponential improvements for quantum-accessible reinforcement learning
• Characterization of a driven two-level quantum system by Supervised Learning
• Storage and retrieval of von Neumann measurements
• Can biological quantum networks solve NP-hard problems?
• Entanglement Detection with Quantum-inspired Kernels and SVMs
• Quantum framework for Reinforcement Learning: Integrating Markov decision process, quantum arithmetic, and trajectory search
• Quadratic Quantum Speedup for Perceptron Training
• Quantum computing and the brain: quantum nets, dessins d'enfants and neural networks
• Quanvolutional Neural Networks for Pneumonia Detection: An Efficient Quantum-Assisted Feature Extraction Paradigm
• Lean classical-quantum hybrid neural network model for image classification
• Quantum Computing Approach for Energy Optimization in a Prosumer Community
• Quantum Technology for Military Applications
• Deep Reinforcement Learning with Quantum-inspired Experience Replay
• Real-time adaptive sensing of nuclear spins by a single-spin quantum sensor
• Experimental semi-autonomous eigensolver using reinforcement learning
• Policy Gradients using Variational Quantum Circuits
• Revisiting the dynamics of Bose-Einstein condensates in a double well by deep learning with a hybrid network
• Do qubits dream of entangled sheep? Quantum measurement without classical output
• A hybrid quantum-classical neural network with deep residual learning
• Multi-party quantum fingerprinting with weak coherent pulses: circuit design and protocol analysis
• Towards violations of Local Friendliness with quantum computers
• Exploring fixed points and eigenstates of quantum systems with reinforcement learning
• Implementation of a Hamming-Distance-Like Genomic Quantum Classifier Using Inner Products on IBMQX4 and IBMQX16
• Quantum spatial best-arm identification via quantum walks
• Noise-Resilient Quantum Reinforcement Learning
• Measuring Incompatible Observables with Quantum Neural Networks