Related references
Note: Only part of the references are listed.
Article
Physics, Multidisciplinary
Kunal Sharma et al.
Summary: The NFL theorem limits one's ability to learn a function with a training dataset. Researchers show that entangled datasets in the quantum environment can lead to a violation of the NFL theorem, and that entanglement can reduce the fundamental limit on the learnability of a unitary.
PHYSICAL REVIEW LETTERS
(2022)
Review
Physics, Multidisciplinary
Kishor Bharti et al.
Summary: NISQ computers, composed of noisy qubits, are already being used in various fields. This review provides a comprehensive summary of NISQ computational paradigms and algorithms and introduces various benchmarking and software tools for programming and testing NISQ devices.
REVIEWS OF MODERN PHYSICS
(2022)
Article
Multidisciplinary Sciences
Dorit Aharonov et al.
Summary: In this study, researchers introduced the framework of quantum algorithmic measurements (QUALMs) to investigate two important experimental problems in quantum physics. They found that if experimental samples can be used coherently in both space and time, a provable exponential speedup can be achieved. The research suggests that quantum computers may provide an exponential advantage in resource savings for quantum experiments.
NATURE COMMUNICATIONS
(2022)
Article
Quantum Science & Technology
Haoyuan Cai et al.
Summary: This article proves that physical quantum circuits can be learned through empirical risk minimization on a quantum computer, and provides valuable guidance for the development of quantum machine learning in both theory and practice.
QUANTUM SCIENCE AND TECHNOLOGY
(2022)
Article
Physics, Multidisciplinary
Yuxuan Du et al.
Summary: This paper investigates the expressivity of VQAs using the covering number tool in statistical learning theory. The expressivity is found to depend on the number of quantum gates and measurement observables, and it exponentially decays with increasing circuit depth under the consideration of system noise. Numerical verification using VQAs with different levels of expressivity is conducted to analyze their applications in QNN generalization and VQE accuracy.
PHYSICAL REVIEW LETTERS
(2022)
Article
Physics, Multidisciplinary
Kunal Sharma et al.
Summary: This article analyzes the gradient scaling performance of a recently proposed architecture called dissipative quantum neural networks (DQNNs), and finds that DQNNs can exhibit gradient vanishing. Moreover, we quantitatively bound the scaling of the gradient for DQNNs under different conditions and demonstrate that trainability is not always guaranteed.
PHYSICAL REVIEW LETTERS
(2022)
Article
Physics, Multidisciplinary
Martin Larocca et al.
Article
Quantum Science & Technology
Junyu Liu et al.
Summary: In this paper, the design and performance prediction of variational quantum circuits for learning and optimization tasks are discussed using the theory of neural tangent kernels. Quantum neural tangent kernels are defined, and dynamical equations for their loss function in optimization tasks are derived. Analytical solutions in the frozen limit and dynamical settings are explored, showing that a hybrid quantum classical neural network has approximate Gaussian behavior.
Article
Optics
Kaifeng Bu et al.
Summary: In this work, the statistical complexity measure, Rademacher complexity, is applied to the quantum circuit model in quantum computation to investigate its dependence on various circuit parameters. The study introduces a magic resource measure based on (p, q) group norm to examine how the statistical complexity scales with circuit resources. The obtained bounds can be used to constrain the capacity of quantum neural networks.
Article
Quantum Science & Technology
Zoe Holmes et al.
Summary: Parametrized quantum circuits are a flexible paradigm for solving variational problems and programming near-term quantum computers. By extending the barren plateau phenomenon to arbitrary ansatze, we establish a fundamental relationship between expressibility and trainability, showing that highly expressive ansatze are more difficult to train.
Article
Multidisciplinary Sciences
G. W. K. Moore et al.
Summary: Ice arches at the northern and southern ends of Nares Strait, a key passage in the Arctic, are forming for shorter durations, leading to increased ice transport and accelerating the export of multi-year ice.
NATURE COMMUNICATIONS
(2021)
Article
Quantum Science & Technology
Tyler Volkoff et al.
Summary: This study demonstrates that reducing the dimensionality of parameter space by utilizing circuit modules containing spatially or temporally correlated gate layers can help avoid the vanishing gradient phenomenon. In the variational versions of Grover's algorithm, as the number of layers increases towards O(2n/2), the bounds on cost function variation suggest a transition from vanishing gradients to efficient trainability.
QUANTUM SCIENCE AND TECHNOLOGY
(2021)
Review
Physics, Multidisciplinary
Suguru Endo et al.
Summary: Quantum computers exploit a Hilbert space with exponentially increasing dimensions, and quantum supremacy has been achieved by a Google team. The potential applications of NISQ devices are still being explored, with hybrid quantum-classical algorithms and error mitigation techniques being key areas of interest.
JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN
(2021)
Article
Multidisciplinary Sciences
Samson Wang et al.
Summary: The study demonstrates that local Pauli noise can render VQAs untrainable. It shows that noise-induced barren plateaus cause the gradient to exponentially vanish during the training process.
NATURE COMMUNICATIONS
(2021)
Article
Physics, Multidisciplinary
A. Uvarov et al.
Summary: The text discusses variational quantum algorithms and the phenomenon of barren plateaus in parametrized quantum circuits, where gradients vanish exponentially. By deriving a lower bound on the variance of the gradient, researchers clarify the conditions under which barren plateaus can occur. The onset of a barren plateau regime is shown to depend on the cost function and the width of the circuit causal cone.
JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL
(2021)
Article
Quantum Science & Technology
Andrew Arrasmith et al.
Summary: Barren plateau landscapes are shown to significantly impact gradient-based optimizers, and this study confirms that gradient-free optimizers are also unable to solve the barren plateau problem. The research reveals the limitations of gradient-free optimization and sheds light on the challenges of training quantum neural networks in barren plateaus.
Article
Quantum Science & Technology
Matthias C. Caro et al.
Summary: Recent research has explored the potential of parametrized quantum circuits (PQCs) as machine learning models, proposing generalization bounds that depend on data-encoding strategies. These results emphasize the importance of well-considered data-encoding strategies for PQC-based models and facilitate optimal strategy selection through structural risk minimization.
Article
Physics, Multidisciplinary
Hsin-Yuan Huang et al.
Summary: The study compares the performance of classical and quantum machine learning models in predicting outcomes of physical experiments, finding that quantum ML models can have exponential advantage in certain cases. While classical ML models can provide accurate average predictions by accessing epsilon a comparable number of times, quantum ML models show the potential for achieving accurate predictions on all inputs.
PHYSICAL REVIEW LETTERS
(2021)
Article
Physics, Multidisciplinary
Zoe Holmes et al.
Summary: In this paper, the authors investigate the possibility of using quantum machine learning to study scrambling processes, and demonstrate the difficulty of learning unknown scrambling processes. The study shows that there are limitations in learning unitaries without prior information.
PHYSICAL REVIEW LETTERS
(2021)
Article
Multidisciplinary Sciences
M. Cerezo et al.
Summary: In this study, the authors rigorously prove that defining cost functions with local observables can avoid the barren plateau problem, while defining them with global observables leads to exponentially vanishing gradients. The results indicate a connection between locality and trainability in variational quantum algorithms (VQAs).
NATURE COMMUNICATIONS
(2021)
Article
Quantum Science & Technology
M. Cerezo et al.
Summary: The phenomenon of barren plateaus in quantum neural networks causes exponential suppression of elements in the Hessian matrix, making estimation at this situation require exponential precision with system size n. This indicates that Hessian-based approaches do not overcome the exponential scaling associated with barren plateaus. Additionally, higher order derivatives are also exponentially suppressed, impacting optimization strategies beyond first-order gradient descent.
QUANTUM SCIENCE AND TECHNOLOGY
(2021)
Article
Physics, Multidisciplinary
Yunchao Liu et al.
Summary: Research shows that heuristic quantum kernel methods can achieve quantum speed-up with only classical data access, and a classification problem is constructed to demonstrate this.
Article
Quantum Science & Technology
Claudiu Marius Popescu
Summary: In this paper, the learnability of hypothesis sets for regression and binary classification defined by quantum circuits is investigated. The learning bounds obtained depend polynomially on the parameters defining the circuits set, and the setting is quite general. Comparison with other bounds in the literature is made to discuss implications for classification and regression on quantum data.
QUANTUM INFORMATION PROCESSING
(2021)
Article
Physics, Multidisciplinary
Korbinian Kottmann et al.
Summary: This study demonstrates mapping out the phase diagram of a two-dimensional quantum many-body system without prior physical knowledge using deep anomaly detection and ground state simulations. The research shows that simple update optimization and post-selecting ground states based on energy can provide a good qualitative picture of transition lines for the 2D frustrated bilayer Heisenberg model. Furthermore, it is shown that more training data does not necessarily lead to better results, with one training example being sufficient for this learning task.
Article
Physics, Multidisciplinary
Korbinian Kottmann et al.
Summary: One promising application of quantum computing is simulating quantum many-body systems, with the proposal of variational quantum anomaly detection algorithm for analyzing quantum data. The algorithm can extract phase diagram of a system without prior knowledge, and can be performed end-to-end on the same quantum device.
PHYSICAL REVIEW RESEARCH
(2021)
Article
Quantum Science & Technology
Leonardo Banchi et al.
Summary: Quantum classification and hypothesis testing are closely related subjects, with the ability to predict the correct class of previously unseen states depending on the mutual information between quantum state space and classical parameter space. Factors such as the dimension of the Hilbert space, noise level, and neglected information from classical data affect classification accuracy and generalization. The introduction of a quantum version of the information bottleneck principle allows for exploration of trade-offs between accuracy and generalization.
Article
Quantum Science & Technology
Carlos Ortiz Marrero et al.
Summary: The article discusses how excess entanglement between visible and hidden units in quantum neural networks can hinder learning. Through arguments from quantum thermodynamics, it is shown that the volume law in entanglement entropy is typical and can lead to barren plateaus in the optimization landscape due to entanglement. This could cause both gradient-descent and gradient-free methods to fail.
Article
Physics, Multidisciplinary
Michael R. Geller et al.
Summary: The study demonstrates learning a two-qubit unitary through parameterized quantum circuits and variational diagonalization for spectral decomposition. This approach can be used to compress the depth of dynamical quantum simulations as only one training data pair is needed to learn a unitary matrix.
PHYSICAL REVIEW RESEARCH
(2021)
Review
Physics, Applied
M. Cerezo et al.
Summary: Variational quantum algorithms, utilizing classical optimizers to train parameterized quantum circuits, have emerged as a leading strategy to address the limitations of quantum computing. Despite challenges, they appear to be the best hope for achieving quantum advantage.
NATURE REVIEWS PHYSICS
(2021)
Article
Physics, Multidisciplinary
Taylor L. Patti et al.
Summary: This study reveals the role of entanglement in barren plateaus, proposes techniques to ameliorate them, and emphasizes the impact of entanglement on training and the avoidability of barren plateaus in the learning process.
PHYSICAL REVIEW RESEARCH
(2021)
Article
Computer Science, Theory & Methods
Chih-Chieh Chen et al.
Summary: This article investigates the use of quantum processors to model high-dimensional function approximators in quantum machine learning. Through simulations and theoretical analysis, it is found that automatic regularization can reduce overfitting issues as the depth of the quantum circuit increases.
ACM TRANSACTIONS ON QUANTUM COMPUTING
(2021)
Article
Computer Science, Interdisciplinary Applications
Amira Abbas et al.
Summary: This study investigates the advantage of near-term quantum computers for machine learning tasks by comparing the power and trainability of quantum machine learning models with classical neural networks. The effective dimension, a data-dependent measure based on Fisher information, is proposed to evaluate a model's ability to generalize on new data. Numerical demonstrations show that quantum neural networks outperform comparable feedforward networks in effective dimension and training speed, indicating an advantage for quantum machine learning validated on real quantum hardware.
NATURE COMPUTATIONAL SCIENCE
(2021)
Article
Quantum Science & Technology
Ho Lun Tang et al.
Summary: The study introduces a new algorithm ADAPT-VQE for quantum simulation, which reduces circuit depths by constructing system-adapted ansatze with fewer parameters. Through numerical simulations, the effectiveness of the new algorithm is validated, significantly reducing circuit depths while maintaining accuracy.
Article
Quantum Science & Technology
Lukasz Cincio et al.
Summary: The paper introduces a machine learning framework, Noise-Aware Circuit Learning (NACL), to reduce the impact of quantum hardware noise on quantum circuits. By minimizing task-specific cost functions, NACL outputs optimized circuits to accomplish tasks in the presence of noise.
Article
Quantum Science & Technology
Jonathan Romero et al.
Summary: A hybrid quantum-classical approach for modeling continuous classical probability distributions using a variational quantum circuit was proposed. The quantum generator architecture includes encoding classical random variables into quantum states and training a parameterized quantum circuit to mimic the target distribution. The model can interface smoothly with classical functions like neural networks, and is trained using an adversarial learning approach.
ADVANCED QUANTUM TECHNOLOGIES
(2021)
Article
Physics, Multidisciplinary
Kunal Sharma et al.
NEW JOURNAL OF PHYSICS
(2020)
Article
Quantum Science & Technology
Yunseong Nam et al.
NPJ QUANTUM INFORMATION
(2020)
Article
Quantum Science & Technology
Jonas M. Kuebler et al.
Article
Physics, Multidisciplinary
Suguru Endo et al.
PHYSICAL REVIEW LETTERS
(2020)
Article
Quantum Science & Technology
Cristina Cirstoiu et al.
NPJ QUANTUM INFORMATION
(2020)
Article
Computer Science, Artificial Intelligence
Matthias C. Caro et al.
QUANTUM MACHINE INTELLIGENCE
(2020)
Article
Quantum Science & Technology
Adrian Perez-Salinas et al.
Article
Multidisciplinary Sciences
Vojtech Havlicek et al.
Article
Multidisciplinary Sciences
Harper R. Grimsley et al.
NATURE COMMUNICATIONS
(2019)
Article
Physics, Multidisciplinary
Iris Cong et al.
Article
Quantum Science & Technology
Sumeet Khatri et al.
Article
Quantum Science & Technology
Jonathan Romero et al.
QUANTUM SCIENCE AND TECHNOLOGY
(2019)
Review
Physics, Multidisciplinary
Vedran Dunjko et al.
REPORTS ON PROGRESS IN PHYSICS
(2018)
Article
Physics, Multidisciplinary
Seth Lloyd et al.
PHYSICAL REVIEW LETTERS
(2018)
Article
Physics, Multidisciplinary
Lukasz Cincio et al.
NEW JOURNAL OF PHYSICS
(2018)
Article
Multidisciplinary Sciences
Jarrod R. McClean et al.
NATURE COMMUNICATIONS
(2018)
Article
Quantum Science & Technology
John Preskill
Article
Optics
Pierre-Luc Dallaire-Demers et al.
Review
Multidisciplinary Sciences
Jacob Biamonte et al.
Article
Quantum Science & Technology
Kwok Ho Wan et al.
NPJ QUANTUM INFORMATION
(2017)
Article
Materials Science, Multidisciplinary
Ruben Verresen et al.
Article
Quantum Science & Technology
Jonathan Romero et al.
QUANTUM SCIENCE AND TECHNOLOGY
(2017)
Article
Physics, Multidisciplinary
Maria Schuld et al.
CONTEMPORARY PHYSICS
(2015)
Article
Physics, Multidisciplinary
Roman Orus
Review
Quantum Science & Technology
Maria Schuld et al.
QUANTUM INFORMATION PROCESSING
(2014)
Article
Materials Science, Multidisciplinary
Andrew J. Ferris et al.
Article
Computer Science, Information Systems
Soraya Taghavi et al.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2010)
Article
Quantum Science & Technology
Robert L. Kosut et al.
QUANTUM INFORMATION PROCESSING
(2009)
Article
Computer Science, Information Systems
Andrew S. Fletcher et al.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2008)
Article
Optics
Andrew S. Fletcher et al.
Article
Physics, Multidisciplinary
Robert L. Kosut et al.
PHYSICAL REVIEW LETTERS
(2008)
Article
Physics, Multidisciplinary
Daniel E. Browne
NEW JOURNAL OF PHYSICS
(2007)
Article
Physics, Multidisciplinary
G. Vidal
PHYSICAL REVIEW LETTERS
(2007)