Quantum Lazy Training

Abstract

In the training of over-parameterized model functions via gradient descent, sometimes the parameters do not change significantly and remain close to their initial values. This phenomenon is called lazy training, and motivates consideration of the linear approximation of the model function around the initial parameters. In the lazy regime, this linear approximation imitates the behavior of the parameterized function whose associated kernel, called the tangent kernel, specifies the training performance of the model. Lazy training is known to occur in the case of (classical) neural networks with large widths. In this paper, we show that the training of geometrically local parameterized quantum circuits enters the lazy regime for large numbers of qubits. More precisely, we prove bounds on the rate of changes of the parameters of such a geometrically local parameterized quantum circuit in the training process, and on the precision of the linear approximation of the associated quantum model function; both of these bounds tend to zero as the number of qubits grows. We support our analytic results with numerical simulations.

arXiv comment19 pages, 7 figures + 5 page appendix (V2: Added a couple of remarks; V3: Fixed typo, updated figure and added URL of GitHub repository; V4: Applied changes after getting reviewed; V5: Fixed typo, V6: Changed format to Quantum template, V7: Change license)

References in corpus (14)

• Quantum Computing in the NISQ era and beyond
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Efficient Learning for Deep Quantum Neural Networks
• Data re-uploading for a universal quantum classifier
• On Lazy Training in Differentiable Programming
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Representation Learning via Quantum Neural Tangent Kernels
• Analytic theory for the dynamics of wide quantum neural networks

Cited by in corpus (1)

• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning