Designing Shadow Tomography Protocols by Natural Language Processing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Yadong, Zhang, Pengfei, Wang, Ce, Yao, Juan, You, Yi-Zhuang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912589601046528
author Wu, Yadong
Zhang, Pengfei
Wang, Ce
Yao, Juan
You, Yi-Zhuang
author_facet Wu, Yadong
Zhang, Pengfei
Wang, Ce
Yao, Juan
You, Yi-Zhuang
contents Quantum circuits form a foundational framework in quantum science, enabling the description, analysis, and implementation of quantum computations. However, designing efficient circuits, typically constructed from single- and two-qubit gates, remains a major challenge for specific computational tasks. In this work, we introduce a novel artificial intelligence-driven protocol for quantum circuit design, benchmarked using shadow tomography for efficient quantum state readout. Inspired by techniques from natural language processing (NLP), our approach first selects a compact gate dictionary by optimizing the entangling power of two-qubit gates. We identify the iSWAP gate as a key element that significantly enhances sample efficiency, resulting in a minimal gate set of {I, SWAP, iSWAP}. Building on this, we implement a recurrent neural network trained via reinforcement learning to generate high-performing quantum circuits. The trained model demonstrates strong generalization ability, discovering efficient circuit architectures with low sample complexity beyond the training set. Our NLP-inspired framework offers broad potential for quantum computation, including extracting properties of logical qubits in quantum error correction.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Designing Shadow Tomography Protocols by Natural Language Processing
Wu, Yadong
Zhang, Pengfei
Wang, Ce
Yao, Juan
You, Yi-Zhuang
Quantum Physics
Quantum circuits form a foundational framework in quantum science, enabling the description, analysis, and implementation of quantum computations. However, designing efficient circuits, typically constructed from single- and two-qubit gates, remains a major challenge for specific computational tasks. In this work, we introduce a novel artificial intelligence-driven protocol for quantum circuit design, benchmarked using shadow tomography for efficient quantum state readout. Inspired by techniques from natural language processing (NLP), our approach first selects a compact gate dictionary by optimizing the entangling power of two-qubit gates. We identify the iSWAP gate as a key element that significantly enhances sample efficiency, resulting in a minimal gate set of {I, SWAP, iSWAP}. Building on this, we implement a recurrent neural network trained via reinforcement learning to generate high-performing quantum circuits. The trained model demonstrates strong generalization ability, discovering efficient circuit architectures with low sample complexity beyond the training set. Our NLP-inspired framework offers broad potential for quantum computation, including extracting properties of logical qubits in quantum error correction.
title Designing Shadow Tomography Protocols by Natural Language Processing
topic Quantum Physics
url https://arxiv.org/abs/2509.12782