Neural Architecture Search Algorithms for Quantum Autoencoders

2025-09-18

AI Summary

Manual design of quantum circuits incurs high labor costs, suffers from poor scalability, and often introduces undesirable inductive biases. Method: This paper proposes an automated architecture search framework tailored for quantum autoencoders—the first application of neural architecture search (NAS) to quantum computing. We design two quantum NAS algorithms that perform task-driven optimization over a structured quantum circuit search space, enabling efficient and low-bias quantum circuit synthesis. Results: Our approach achieves significant performance gains over baseline methods across three distinct tasks: quantum data denoising, classical data compression, and pure quantum data compression—demonstrating both effectiveness and strong generalization capability. This work establishes a novel, scalable paradigm for designing quantum circuits for complex algorithms and advances the automation of quantum machine learning.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The design of quantum circuits is currently driven by the specific objectives of the quantum algorithm in question. This approach thus relies on a significant manual effort by the quantum algorithm designer to design an appropriate circuit for the task. However this approach cannot scale to more complex quantum algorithms in the future without exponentially increasing the circuit design effort and introducing unwanted inductive biases. Motivated by this observation, we propose to automate the process of cicuit design by drawing inspiration from Neural Architecture Search (NAS). In this work, we propose two Quantum-NAS algorithms that aim to find efficient circuits given a particular quantum task. We choose quantum data compression as our driver quantum task and demonstrate the performance of our algorithms by finding efficient autoencoder designs that outperform baselines on three different tasks - quantum data denoising, classical data compression and pure quantum data compression. Our results indicate that quantum NAS algorithms can significantly alleviate the manual effort while delivering performant quantum circuits for any given task.

Problem

• Automating quantum circuit design to reduce manual effort
• Finding efficient quantum autoencoders for data compression tasks
• Overcoming scalability limitations in complex quantum algorithm design

Innovation

• Automated quantum circuit design using NAS
• Two Quantum-NAS algorithms for efficient circuits
• Outperforms baselines in quantum data compression