The dilemma of quantum neural networks

Abstract

The core of quantum machine learning is to devise quantum models with good trainability and low generalization error bound than their classical counterparts to ensure better reliability and interpretability. Recent studies confirmed that quantum neural networks (QNNs) have the ability to achieve this goal on specific datasets. With this regard, it is of great importance to understand whether these advantages are still preserved on real-world tasks. Through systematic numerical experiments, we empirically observe that current QNNs fail to provide any benefit over classical learning models. Concretely, our results deliver two key messages. First, QNNs suffer from the severely limited effective model capacity, which incurs poor generalization on real-world datasets. Second, the trainability of QNNs is insensitive to regularization techniques, which sharply contrasts with the classical scenario. These empirical results force us to rethink the role of current QNNs and to design novel protocols for solving real-world problems with quantum advantages.

References in corpus (27)

• Adam: A Method for Stochastic Optimization
• A variational eigenvalue solver on a quantum processor
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Error mitigation for short-depth quantum circuits
• Extending the computational reach of a noisy superconducting quantum processor
• Quantum Computational Supremacy
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Efficient Learning for Deep Quantum Neural Networks
• The quest for a Quantum Neural Network
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Robust data encodings for quantum classifiers
• Information-theoretic bounds on quantum advantage in machine learning
• Learning-based quantum error mitigation
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Optimization for deep learning: theory and algorithms
• Efficient measure for the expressivity of variational quantum algorithms
• Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms
• Towards understanding the power of quantum kernels in the NISQ era
• Quantum approximate optimization is computationally universal
• Quantum embeddings for machine learning
• On the statistical complexity of quantum circuits
• A Grover-search Based Quantum Learning Scheme for Classification

Cited by in corpus (5)

• Biology and medicine in the landscape of quantum advantages
• Playing Atari with Hybrid Quantum-Classical Reinforcement Learning
• On exploring the potential of quantum auto-encoder for learning quantum systems
• Bayesian Learning of Parameterised Quantum Circuits
• Accelerating variational quantum algorithms with multiple quantum processors