Quantitative Convergence of Trained Quantum Neural Networks to a Gaussian Process
Open Access
- 8 October 2025
- journal article
- research article
- Published by Springer Nature in Annales Henri Poincare
- Vol. 27 (11) , 4011-4067
Abstract
We study quantum neural networks where the generated function is the expectation value of the sum of single-qubit observables across all qubits. In (Girardi et al., CMP (2025), it is proven that the probability distributions of such generated functions converge in distribution to a Gaussian process in the limit of infinite width for both untrained networks with randomly initialized parameters and trained networks. In this paper, we provide a quantitative proof of this convergence in terms of the Wasserstein distance of order 1. First, we establish an upper bound on the distance between the probability distribution of the function generated by any untrained network with finite width and the Gaussian process with the same covariance. This proof utilizes Stein’s method to estimate the Wasserstein distance of order 1. Next, we analyze the training dynamics of the network via gradient flow, proving an upper bound on the distance between the probability distribution of the function generated by the trained network and the corresponding Gaussian process. This proof is based on a quantitative upper bound on the maximum variation of a parameter during training. This bound implies that for sufficiently large widths, training occurs in the lazy regime, i.e., each parameter changes only by a small amount. While the convergence result of Girardi et al., CMP (2025) holds at a fixed training time, our upper bounds are uniform in time and hold even as $$t \rightarrow \infty $$ .
Keywords
All Related Versions
Funding Information
- Narodowe Centrum Nauki (2022WHZ5XH – CUP J53D23003890006)
- Narodowe Centrum Nauki (project SERICS (PE00000014))
- Alma Mater Studiorum - Università di Bologna
This publication has 50 references indexed in Scilit:
- Toward Useful Quantum KernelsAdvanced Quantum Technologies, 2024
- Concise Guide to Quantum Machine Learning2023
- Quantum Optimal Transport with Quantum ChannelsAnnales Henri Poincare, 2021
- Variational Methods for Machine Learning with Applications to Deep Networks2021
- An Invitation to Statistics in Wasserstein Space2020
- A Primer on Quantum Computing2019
- Supervised Learning with Quantum Computers2018
- Dependency graphs and mod-Gaussian convergence2016
- A Probability Metrics Approach to Financial Risk Measures2011
- Optimal Transport2009