Saved in:
Bibliographic Details
Main Authors: Morohoshi, Yuto, Nakayama, Akimoto, Manabe, Hidetaka, Mitarai, Kosuke
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.16370
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909604253794304
author Morohoshi, Yuto
Nakayama, Akimoto
Manabe, Hidetaka
Mitarai, Kosuke
author_facet Morohoshi, Yuto
Nakayama, Akimoto
Manabe, Hidetaka
Mitarai, Kosuke
contents We propose a quantum machine learning task that is provably easy for quantum computers and arguably hard for classical ones. The task involves predicting quantities of the form $\mathrm{Tr}[f(H)ρ]$, where $f$ is an unknown function, given descriptions of $H$ and $ρ$. Using a Fourier-based feature map of Hamiltonians and linear regression, we theoretically establish the learnability of the task and implement it on a superconducting device using up to 40 qubits. This work provides a machine learning task with practical relevance, provable quantum easiness, and near-term feasibility.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16370
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning functions of Hamiltonians with Hamiltonian Fourier features
Morohoshi, Yuto
Nakayama, Akimoto
Manabe, Hidetaka
Mitarai, Kosuke
Quantum Physics
We propose a quantum machine learning task that is provably easy for quantum computers and arguably hard for classical ones. The task involves predicting quantities of the form $\mathrm{Tr}[f(H)ρ]$, where $f$ is an unknown function, given descriptions of $H$ and $ρ$. Using a Fourier-based feature map of Hamiltonians and linear regression, we theoretically establish the learnability of the task and implement it on a superconducting device using up to 40 qubits. This work provides a machine learning task with practical relevance, provable quantum easiness, and near-term feasibility.
title Learning functions of Hamiltonians with Hamiltonian Fourier features
topic Quantum Physics
url https://arxiv.org/abs/2504.16370