---
title: "量子多体系统时间演化的可证明学习分离：量子机器学习优势的理论证明"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.06472v1"
permalink: "https://feed.astralor.com/items/itm_eb33b0513d997713bf74a98b"
published: "2026-07-07T16:30:09.000Z"
score: 74
channel: "tech"
tags: ["PAC学习理论","哈密顿量演化","学习分离","量子机器学习","量子模拟"]
---

# 量子多体系统时间演化的可证明学习分离：量子机器学习优势的理论证明

## AI 点评

> 这篇论文是量子机器学习领域的重要理论突破，它告诉我们量子计算机在特定学习任务上确实拥有不可替代的优势。对于量子计算理论研究者、量子算法设计者以及关注量子优势证明的学者而言，这是一篇必读文献。它的学习分离结果不仅深化了我们对量子学习能力的理解，还为未来设计更实际的量子学习任务提供了理论指导。

## 速览

该论文从PAC学习理论出发，严格证明了量子机器学习在预测量子多体系统时间演化任务上相对于经典算法的学习分离。作者设计了一个监督学习问题：训练集包含随机稳定子探针态、均匀采样时间及观测期望值，并给出高效量子程序（训练阶段学习哈密顿量，部署阶段结合哈密顿模拟与经典阴影协议）。通过将BQP完全问题嵌入Feynman-Kitaev时钟哈密顿量的低交叉变体，证明经典多项式时间算法无法满足学习条件（除非BQP⊆P/poly），而量子算法仍可学习。结果建立了量子学习理论、量子模拟与量子机器学习之间的联系，并具有学习辅助认证量子模拟的潜在应用。

## 关键点

- 提出了量子多体系统时间演化预测的监督学习任务，并给出了高效量子算法（训练+部署）。
- 通过将BQP完全问题嵌入Feynman-Kitaev时钟哈密顿量，证明了经典多项式时间算法的不可行性（除非BQP⊆P/poly）。
- 该学习分离为量子机器学习优势提供了严格的PAC学习理论依据。
- 结果在学习辅助认证量子模拟中具有潜在应用价值。

## 全文

Given that quantum computers are naturally suited to simulate the behavior of quantum many-body systems, an immediate question arises: can one formulate physically motivated quantum machine learning (QML) tasks that exhibit learning separations? We address this problem by studying the learnability of quantum many-body dynamics from the perspective of probably approximately correct (PAC)-learning. Concretely, we devise a supervised learning problem where the training set consists of specifications of randomized stabilizer probe states, evolution times sampled uniformly from a polynomially large time interval $[0,T]$, coupled with expectation values of certain observables evaluated on the resulting time-evolved state under an unknown Hamiltonian. For this learning task, we provide an efficient quantum procedure whose training phase learns the underlying Hamiltonian from short-time training samples, and whose deployment phase combines Hamiltonian simulation with the classical shadows protocol to perform inference on a newly given data point. By contrast, the existence of $O(\mathsf{poly}(n))$-time instances ensures classical hardness: by embedding a $\mathsf{BQP}$-complete computation into the polynomially long time-dynamics of a low-intersection variant of the Feynman-Kitaev clock Hamiltonian construction, we show that, for a certain family of input distributions, no randomized classical polynomial-time algorithm can fulfill our learning condition, unless $\mathsf{BQP}\subseteq\mathsf{P/poly}$. Furthermore, we show that the classically hard instance maintains quantum learnability. We also give an interpretation of our results in learning-assisted certified quantum simulation. Taken together, our results demonstrate a rigorous learning separation for a natural ML task based on Hamiltonian evolution, while building connections between quantum learning theory, quantum simulation, and QML.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_eb33b0513d997713bf74a98b