The quantum cost function concentration dependency on the parametrization expressivity

Abstract

Although we are currently in the era of noisy intermediate scale quantum devices, several studies are being conducted with the aim of bringing machine learning to the quantum domain. Currently, quantum variational circuits are one of the main strategies used to build such models. However, despite its widespread use, we still do not know what are the minimum resources needed to create a quantum machine learning model. In this article, we analyze how the expressiveness of the parametrization affects the cost function. We analytically show that the more expressive the parametrization is, the more the cost function will tend to concentrate around a value that depends both on the chosen observable and on the number of qubits used. For this, we initially obtain a relationship between the expressiveness of the parametrization and the mean value of the cost function. Afterwards, we relate the expressivity of the parametrization with the variance of the cost function. Finally, we show some numerical simulation results that confirm our theoretical-analytical predictions. To the best of our knowledge, this is the first time that these two important aspects of quantum neural networks are explicitly connected.

References in corpus (25)

• Quantum algorithm for solving linear systems of equations
• Variational Quantum Algorithms
• Barren plateaus in quantum neural network training landscapes
• Quantum Convolutional Neural Networks
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Integration with respect to the Haar measure on unitary, orthogonal and symplectic group
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum generative adversarial learning
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Layerwise learning for quantum neural networks
• Robust data encodings for quantum classifiers
• Hybrid Quantum-Classical Convolutional Neural Networks
• Experimental Quantum Generative Adversarial Networks for Image Generation
• Effect of barren plateaus on gradient-free optimization
• Differentiable Quantum Architecture Search
• Large gradients via correlation in random parameterized quantum circuits
• Entanglement Devised Barren Plateau Mitigation
• On barren plateaus and cost function locality in variational quantum algorithms
• Avoiding Barren Plateaus with Classical Deep Neural Networks
• Natural Evolutionary Strategies for Variational Quantum Computation
• Hybrid quantum-classical neural network for calculating ground state energies of molecules
• Evolution strategies: Application in hybrid quantum-classical neural networks

Cited by in corpus (9)

• Barren Plateaus in Variational Quantum Computing
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Does provable absence of barren plateaus imply classical simulability?
• Emergence of noise-induced barren plateaus in arbitrary layered noise models
• Restricting to the chip architecture maintains the quantum neural network accuracy
• Learning to learn with an evolutionary strategy applied to variational quantum algorithms
• Determining the ability for universal quantum computing: Testing controllability via dimensional expressivity
• Barren plateaus are amplified by the dimension of qudits
• A variational quantum algorithm for entanglement quantification