Learning to Concatenate Quantum Codes

2026/04/16 by Nico Meyer, Christopher Mutschler, Dominik Seuß +2 · 1 voice
Computer Science · Engineering · Physics and Astronomy · #Code (set theory) #Encoder #Error detection and correction #Noise (video) #Quantum Computing Algorithms and Architecture #Quantum Information and Cryptography #Quantum convolutional code #Quantum error correction #Qubit #Radiation Effects in Electronics #Turbo code #cs.LG #quant-ph

paper · pdf · doi:10.48550/arxiv.2604.14931

openalex publication_date 2026/04/16 · arxiv published 2026/04/16 · arxiv updated 2026/04/16 · openalex created_date 2026/04/18 · openalex updated_date 2026/07/28

Abstract

Concatenating quantum error correction codes scales error correction capability by driving logical error rates down double-exponentially across levels. However, the noise structure shifts under concatenation, making it hard to choose an optimal code sequence. We automate this choice by estimating the effective noise channel after each level and selecting the next code accordingly. In particular, we use learning-based methods to tailor small, non-additive encoders when the noise exhibits sufficient structure, then switch to standard codes once the noise is nearly uniform. In simulations, this level-wise adaptation achieves a target logical error rate with far fewer qubits than concatenating stabilizer codes alone--reducing qubit counts by up to two orders of magnitude for strongly structured noise. Therefore, this hybrid, learning-based strategy offers a promising tool for early fault-tolerant quantum computing.

Citations

• Scaling the Automated Discovery of Quantum Circuits via Reinforcement Learning with Gadgets
• Concatenate codes, save qubits
• Simultaneous Discovery of Quantum Error Correction Codes and Encoders with a Noise-Aware Reinforcement Learning Agent
• A Quantum Engineer's Guide to Superconducting Qubits
• Characterizing large-scale quantum computers via cycle benchmarking
• Optimizing Quantum Error Correction Codes with Reinforcement Learning
• Robustness of the concatenated quantum error-correction protocol against noise for channels affected by fluctuation
• The Theory of Quantum Information
• Reinforcement Learning with Neural Networks for Quantum Feedback
• QVECTOR: an algorithm for device-tailored quantum error correction
• Introduction to Quantum Gate Set Tomography
• Efficient error models for fault-tolerant architectures and the Pauli twirling approximation
• Quantum t-designs: t-wise independence in the quantum world
• Exact and approximate unitary 2-designs and their application to fidelity estimation
• Quantum accuracy threshold for concatenated distance-3 codes
• Approximate quantum error correction
• Stabilizer Codes and Quantum Error Correction
• Concatenated Quantum Codes
• Perfect Quantum Error Correction Code
• On the limited memory BFGS method for large scale optimization
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Discussions

• Learning to Concatenate Quantum Codes This article tackles one of quantum computing's most pressing challenges: how to efficiently build up error correction by stacking multiple layers of quantum code [bsky, 0 points, 0 comments]

Related

• Learning Encodings by Maximizing State Distinguishability: Variational Quantum Error Correction
• Noise-strength-adapted approximate quantum codes inspired by machine learning
• Discovering highly efficient low-weight quantum error-correcting codes with reinforcement learning
• Error tracing in linear and concatenated quantum circuits
• Real-time adaptive quantum error correction by model-free multi-agent learning