Trained quantum neural networks are Gaussian processes

DOI10.1007/S00220-025-05238-0MaRDI QIDQ7001138zbMATH OpenFDO

Authors Filippo Girardi, Giacomo De Palma

Publication date 7 April 2025

Published in Communications in Mathematical Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S00220-025-05238-0

zbMATH Keywords

convergence in distributionGaussian processesquantum neural networks

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Gaussian processes (60G15) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Artificial neural networks and deep learning (68T07) Quantum information, communication, networks (quantum-theoretic aspects) (81P45) Quantum gates (81P65)

Cites work

• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
• A Remark on Stirling's Formula
• Asymptotic Statistics
• Bayesian learning for neural networks
• Concentration inequalities. A nonasymptotic theory of independence
• Deep learning
• Foundations of modern probability. In 2 volumes
• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 1354815 (Why is no real title available?)
• scientific article; zbMATH DE number 3238721 (Why is no real title available?)
• Mod- convergence. Normality zones and precise deviations
• Moderate deviations via cumulants
• Neural tangent kernel: convergence and generalization in neural networks (invited paper)
• Normal convergence by higher semi-invariants with applications to sums of dependent random variables and random graphs
• PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
• Probability with Martingales
• Product-state approximations to quantum states
• Random neural networks in the infinite width limit as Gaussian processes
• The method of cumulants for the normal approximation
• The Quantum Wasserstein Distance of Order 1
• Wide neural networks of any depth evolve as linear models under gradient descent ^*
• Über stochastische Asymptoten und Grenzwerte.

Cited in

(1)

• Mean-field limit from general mixtures of experts to quantum neural networks

This page was built for publication: Trained quantum neural networks are Gaussian processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7001138)