Subtleties in the trainability of quantum machine learning models

Abstract

A new paradigm for data science has emerged, with quantum data, quantum models, and quantum computational devices. This field, called Quantum Machine Learning (QML), aims to achieve a speedup over traditional machine learning for data analysis. However, its success usually hinges on efficiently training the parameters in quantum neural networks, and the field of QML is still lacking theoretical scaling results for their trainability. Some trainability results have been proven for a closely related field called Variational Quantum Algorithms (VQAs). While both fields involve training a parametrized quantum circuit, there are crucial differences that make the results for one setting not readily applicable to the other. In this work we bridge the two frameworks and show that gradient scaling results for VQAs can also be applied to study the gradient scaling of QML models. Our results indicate that features deemed detrimental for VQA trainability can also lead to issues such as barren plateaus in QML. Consequently, our work has implications for several QML proposals in the literature. In addition, we provide theoretical and numerical evidence that QML models exhibit further trainability issues not present in VQAs, arising from the use of a training dataset. We refer to these as dataset-induced barren plateaus. These results are most relevant when dealing with classical data, as here the choice of embedding scheme (i.e., the map between classical data and quantum states) can greatly affect the gradient scaling.

12+12 pages, 8+2 figures

References in corpus (20)

• Variational Quantum Algorithms
• An introduction to quantum machine learning
• The power of quantum neural networks
• The quest for a Quantum Neural Network
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Generalization in quantum machine learning from few training data
• Classical simulation of commuting quantum computations implies collapse of the polynomial hierarchy
• Information-theoretic bounds on quantum advantage in machine learning
• Effect of barren plateaus on gradient-free optimization
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Training Quantum Embedding Kernels on Near-Term Quantum Computers
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Entanglement Devised Barren Plateau Mitigation
• Efficient measure for the expressivity of variational quantum algorithms
• Quantum Algorithmic Measurement
• Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning

Cited by in corpus (5)

• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• On the practical usefulness of the Hardware Efficient Ansatz
• The battle of clean and dirty qubits in the era of partial error correction