Evolution strategies: Application in hybrid quantum-classical neural networks

Abstract

With the rapid development of quantum computers, several applications are being proposed for them. Quantum simulations, simulation of chemical reactions, solution of optimization problems and quantum neural networks (QNNs) are some examples. However, problems such as noise, limited number of qubits and circuit depth, and gradient vanishing must be resolved before we can use them to their full potential. In the field of quantum machine learning, several models have been proposed. In general, in order to train these different models, we use the gradient of a cost function with respect to the model parameters. In order to obtain this gradient, we must compute the derivative of this function with respect to the model parameters. One of the most used methods in the literature to perform this task is the parameter-shift rule method. This method consists of evaluating the cost function twice for each parameter of the QNN. A problem with this method is that the number of evaluations grows linearly with the number of parameters. In this work we study an alternative method, called Evolution Strategies (ES), which are a family of black box optimization algorithms which iteratively update the parameters using a search gradient. An advantage of the ES method is that in using it one can control the number of times the cost function will be evaluated. We apply the ES method to the binary classification task, showing that this method is a viable alternative for training QNNs. However, we observe that its performance will be strongly dependent on the hyperparameters used. Furthermore, we also observe that this method, alike the parameter shift rule method, suffers from the problem of gradient vanishing.

References in corpus (19)

• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Efficient Learning for Deep Quantum Neural Networks
• Data re-uploading for a universal quantum classifier
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• 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
• Effect of barren plateaus on gradient-free optimization
• Large gradients via correlation in random parameterized quantum circuits
• Entanglement Devised Barren Plateau Mitigation
• Quantum implementation of an artificial feed-forward neural network
• Avoiding Barren Plateaus with Classical Deep Neural Networks
• Deep Learning for Image Sequence Classification of Astronomical Events
• Natural Evolutionary Strategies for Variational Quantum Computation
• Hybrid quantum-classical neural network for calculating ground state energies of molecules

Cited by in corpus (5)

• The quantum cost function concentration dependency on the parametrization expressivity
• Restricting to the chip architecture maintains the quantum neural network accuracy
• Learning to learn with an evolutionary strategy applied to variational quantum algorithms
• Barren plateaus are amplified by the dimension of qudits
• A variational quantum algorithm for entanglement quantification