A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nguyen, Hoang Viet, Nguyen, Manh Hung, Ta, Hoang, Vu, Van Khu, Chee, Yeow Meng
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915957190950912
author Nguyen, Hoang Viet
Nguyen, Manh Hung
Ta, Hoang
Vu, Van Khu
Chee, Yeow Meng
author_facet Nguyen, Hoang Viet
Nguyen, Manh Hung
Ta, Hoang
Vu, Van Khu
Chee, Yeow Meng
contents Quantum error correction is a key ingredient for large scale quantum computation, protecting logical information from physical noise by encoding it into many physical qubits. Topological stabilizer codes are particularly appealing due to their geometric locality and practical relevance. In these codes, stabilizer measurements yield a syndrome that must be decoded into a recovery operation, making decoding a central bottleneck for scalable real time operation. Existing decoders are commonly classified into two categories. Classical algorithmic decoders provide strong and well established baselines, but may incur substantial computational overhead at large code distances or under stringent latency constraints. Machine learning based decoders offer fast GPU inference and flexible function approximation, yet many approaches do not explicitly exploit the lattice geometry and local structure of topological codes, which can limit performance. In this work, we propose QuantumSMoE, a quantum vision transformer based decoder that incorporates code structure through plus shaped embeddings and adaptive masking to capture local interactions and lattice connectivity, and improves scalability via a mixture of experts layer with a novel auxiliary loss. Experiments on the toric code demonstrate that QuantumSMoE outperforms state-of-the-art machine learning decoders as well as widely used classical baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12483
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding
Nguyen, Hoang Viet
Nguyen, Manh Hung
Ta, Hoang
Vu, Van Khu
Chee, Yeow Meng
Quantum Physics
Information Theory
Machine Learning
Quantum error correction is a key ingredient for large scale quantum computation, protecting logical information from physical noise by encoding it into many physical qubits. Topological stabilizer codes are particularly appealing due to their geometric locality and practical relevance. In these codes, stabilizer measurements yield a syndrome that must be decoded into a recovery operation, making decoding a central bottleneck for scalable real time operation. Existing decoders are commonly classified into two categories. Classical algorithmic decoders provide strong and well established baselines, but may incur substantial computational overhead at large code distances or under stringent latency constraints. Machine learning based decoders offer fast GPU inference and flexible function approximation, yet many approaches do not explicitly exploit the lattice geometry and local structure of topological codes, which can limit performance. In this work, we propose QuantumSMoE, a quantum vision transformer based decoder that incorporates code structure through plus shaped embeddings and adaptive masking to capture local interactions and lattice connectivity, and improves scalability via a mixture of experts layer with a novel auxiliary loss. Experiments on the toric code demonstrate that QuantumSMoE outperforms state-of-the-art machine learning decoders as well as widely used classical baselines.
title A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding
topic Quantum Physics
Information Theory
Machine Learning
url https://arxiv.org/abs/2601.12483