Analytic theory for the dynamics of wide quantum neural networks

Abstract

Parameterized quantum circuits can be used as quantum neural networks and have the potential to outperform their classical counterparts when trained for addressing learning problems. To date, much of the results on their performance on practical problems are heuristic in nature. In particular, the convergence rate for the training of quantum neural networks is not fully understood. Here, we analyze the dynamics of gradient descent for the training error of a class of variational quantum machine learning models. We define wide quantum neural networks as parameterized quantum circuits in the limit of a large number of qubits and variational parameters. We then find a simple analytic formula that captures the average behavior of their loss function and discuss the consequences of our findings. For example, for random quantum circuits, we predict and characterize an exponential decay of the residual training error as a function of the parameters of the system. We finally validate our analytic results with numerical experiments.

37 pages, many figures. v2, v3: adding learning supervised perspectives and new results, close to published version

References in corpus (3)

• An introduction to quantum machine learning
• Is quantum advantage the right goal for quantum machine learning?
• Representation Learning via Quantum Neural Tangent Kernels

Cited by in corpus (21)

• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Quantum-centric Supercomputing for Materials Science: A Perspective on Challenges and Future Directions
• Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization
• An Expressive Ansatz for Low-Depth Quantum Approximate Optimisation
• Quantum Phase Processing and its Applications in Estimating Phase and Entropies
• Effects of noise on the overparametrization of quantum neural networks
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning
• Pulse-efficient quantum machine learning
• Stochastic noise can be helpful for variational quantum algorithms
• GSQAS: Graph Self-supervised Quantum Architecture Search
• Quantum Lazy Training
• Energy-dependent barren plateau in bosonic variational quantum circuits
• Laziness, Barren Plateau, and Noise in Machine Learning
• SnCQA: A hardware-efficient equivariant quantum convolutional circuit architecture
• Trained quantum neural networks are Gaussian processes
• SU(d)-Symmetric Random Unitaries: Quantum Scrambling, Error Correction, and Machine Learning
• Dynamical transition in controllable quantum neural networks with large depth
• Quantum-data-driven dynamical transition in quantum learning
• Double descent in quantum kernel methods
• Gradient Scalability and Taylor Surrogation of Quantum Cost Landscapes