Untrained Filtering with Trained Focusing for Superior Quantum Architecture Search

TL;DR

This paper introduces QUEST-A, a novel quantum architecture search framework that combines untrained filtering and trained focusing to improve search efficiency and accuracy in quantum machine learning tasks.

Contribution

The paper presents QUEST-A, a new framework that integrates coarse untrained filtering with fine-trained focusing, enabling dynamic, multi-level knowledge transfer for superior quantum architecture search.

Findings

Outperforms existing methods in model expressivity and performance.

Achieves significant precision improvements in variational quantum eigensolver tasks.

Maintains high accuracy across diverse image classification complexities.

Abstract

Quantum architecture search (QAS) represents a fundamental challenge in quantum machine learning. Unlike previous methods that treat it as a static search process, from a perspective on QAS as an item retrieval task in vast search space, we decompose the search process into dynamic alternating phases of coarse and fine-grained knowledge learning. We propose quantum untrained-explored synergistic trained architecture (QUEST-A),a framework through coarse-grained untrained filtering for rapid search space reduction and fine-grained trained focusing for precise space refinement in progressive QAS. QUEST-A develops an evolutionary mechanism with knowledge accumulation and reuse to enhance multi-level knowledge transfer in architecture searching. Experiments demonstrate QUEST-A's superiority over existing methods: enhancing model expressivity in signal representation, maintaining high performance across varying complexities in image classification, and achieving order-of-magnitude precision improvements in variational quantum eigensolver tasks, providing a transferable methodology for QAS.