Avoiding Barren Plateaus with Classical Deep Neural Networks

Abstract

Variational quantum algorithms (VQAs) are among the most promising algorithms in the era of Noisy Intermediate Scale Quantum Devices. Such algorithms are constructed using a parameterization U($\theta$) with a classical optimizer that updates the parameters $\theta$ in order to minimize a cost function $C$. For this task, in general the gradient descent method, or one of its variants, is used. This is a method where the circuit parameters are updated iteratively using the cost function gradient. However, several works in the literature have shown that this method suffers from a phenomenon known as the Barren Plateaus (BP). In this work, we propose a new method to mitigate BPs. In general, the parameters $\theta$ used in the parameterization $U$ are randomly generated. In our method they are obtained from a classical neural network (CNN). We show that this method, besides to being able to mitigate BPs during startup, is also able to mitigate the effect of BPs during the VQA training. In addition, we also show how this method behaves for different CNN architectures.

References in corpus (18)

• Quantum algorithm for solving linear systems of equations
• Variational Quantum Algorithms
• Barren plateaus in quantum neural network training landscapes
• 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
• 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
• Effect of barren plateaus on gradient-free optimization
• Large gradients via correlation in random parameterized quantum circuits
• Entanglement Devised Barren Plateau Mitigation
• Expressibility of the alternating layered ansatz for quantum computation
• Quantum Natural Language Processing on Near-Term Quantum Computers

Cited by in corpus (4)

• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• The quantum cost function concentration dependency on the parametrization expressivity
• Evolution strategies: Application in hybrid quantum-classical neural networks
• Restricting to the chip architecture maintains the quantum neural network accuracy