Learning properties of quantum states without the IID assumption

Abstract We develop a framework for learning properties of quantum states beyond the assumption of independent and identically distributed (i.i.d.) input states. We prove that, given any learning problem (under reasonable assumptions), an algorithm designed for i.i.d. input states can be adapted to...

Full description

Saved in:
Bibliographic Details
Main Authors: Omar Fawzi, Richard Kueng, Damian Markham, Aadil Oufkir
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-024-53765-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850196545198096384
author Omar Fawzi
Richard Kueng
Damian Markham
Aadil Oufkir
author_facet Omar Fawzi
Richard Kueng
Damian Markham
Aadil Oufkir
author_sort Omar Fawzi
collection DOAJ
description Abstract We develop a framework for learning properties of quantum states beyond the assumption of independent and identically distributed (i.i.d.) input states. We prove that, given any learning problem (under reasonable assumptions), an algorithm designed for i.i.d. input states can be adapted to handle input states of any nature, albeit at the expense of a polynomial increase in training data size (aka sample complexity). Importantly, this polynomial increase in sample complexity can be substantially improved to polylogarithmic if the learning algorithm in question only requires non-adaptive, single-copy measurements. Among other applications, this allows us to generalize the classical shadow framework to the non-i.i.d. setting while only incurring a comparatively small loss in sample efficiency. We leverage permutation invariance and randomized single-copy measurements to derive a new quantum de Finetti theorem that mainly addresses measurement outcome statistics and, in turn, scales much more favorably in Hilbert space dimension.
format Article
id doaj-art-abcba239ae264c81898611291f3ac5e3
institution OA Journals
issn 2041-1723
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-abcba239ae264c81898611291f3ac5e32025-08-20T02:13:26ZengNature PortfolioNature Communications2041-17232024-11-0115111910.1038/s41467-024-53765-6Learning properties of quantum states without the IID assumptionOmar Fawzi0Richard Kueng1Damian Markham2Aadil Oufkir3Inria, ENS Lyon, UCBL, LIPDepartment of Quantum Information and Computation at Kepler (QUICK), Johannes Kepler University LinzSorbonne Université, CNRSInria, ENS Lyon, UCBL, LIPAbstract We develop a framework for learning properties of quantum states beyond the assumption of independent and identically distributed (i.i.d.) input states. We prove that, given any learning problem (under reasonable assumptions), an algorithm designed for i.i.d. input states can be adapted to handle input states of any nature, albeit at the expense of a polynomial increase in training data size (aka sample complexity). Importantly, this polynomial increase in sample complexity can be substantially improved to polylogarithmic if the learning algorithm in question only requires non-adaptive, single-copy measurements. Among other applications, this allows us to generalize the classical shadow framework to the non-i.i.d. setting while only incurring a comparatively small loss in sample efficiency. We leverage permutation invariance and randomized single-copy measurements to derive a new quantum de Finetti theorem that mainly addresses measurement outcome statistics and, in turn, scales much more favorably in Hilbert space dimension.https://doi.org/10.1038/s41467-024-53765-6
spellingShingle Omar Fawzi
Richard Kueng
Damian Markham
Aadil Oufkir
Learning properties of quantum states without the IID assumption
Nature Communications
title Learning properties of quantum states without the IID assumption
title_full Learning properties of quantum states without the IID assumption
title_fullStr Learning properties of quantum states without the IID assumption
title_full_unstemmed Learning properties of quantum states without the IID assumption
title_short Learning properties of quantum states without the IID assumption
title_sort learning properties of quantum states without the iid assumption
url https://doi.org/10.1038/s41467-024-53765-6
work_keys_str_mv AT omarfawzi learningpropertiesofquantumstateswithouttheiidassumption
AT richardkueng learningpropertiesofquantumstateswithouttheiidassumption
AT damianmarkham learningpropertiesofquantumstateswithouttheiidassumption
AT aadiloufkir learningpropertiesofquantumstateswithouttheiidassumption