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.

arXiv comment12+12 pages, 8+2 figures

References in corpus (45)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• An introduction to quantum machine learning
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Evaluating analytic gradients on quantum hardware
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• Circuit-centric quantum classifiers
• The power of quantum neural networks
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• Efficient Learning for Deep 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
• Quantum-assisted quantum compiling
• Robust data encodings for quantum classifiers
• IBM Q Experience as a versatile experimental testbed for simulating open quantum systems
• Classical simulation of commuting quantum computations implies collapse of the polynomial hierarchy
• Information-theoretic bounds on quantum advantage in machine learning
• Variational quantum simulation of general processes
• 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
• Noise Resilience of Variational Quantum Compiling
• Variational algorithms for linear algebra
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• 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
• Barren plateaus preclude learning scramblers
• Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
• 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
• On Hastings' counterexamples to the minimum output entropy additivity conjecture
• Characterizing the loss landscape of variational quantum circuits
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Expressibility and trainability of parameterized analog quantum systems for machine learning applications

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