Neural Decoders for Universal Quantum Algorithms

Abstract

Fault-tolerant quantum computing demands decoders that are fast, accurate, and adaptable to circuit structure and realistic noise. While machine learning (ML) decoders have demonstrated impressive performance for quantum memory, their use in algorithmic decoding - where logical gates create complex error correlations - remains limited. We introduce a modular attention-based neural decoder that learns gate-induced correlations and generalizes from training on random circuits to unseen multi-qubit algorithmic workloads. Our decoders achieve fast inference and logical error rates comparable to most-likely-error (MLE) decoders across varied circuit depths and qubit counts. Addressing realistic noise, we incorporate loss-resolving readout, yielding substantial gains when qubit loss is present. We further show that by tailoring the decoder to the structure of the algorithm and decoding only the relevant observables, we can simplify the decoder design without sacrificing accuracy. We validate our framework on multiple error correction codes - including surface codes and 2D color codes - and demonstrate state-of-the-art performance under circuit-level noise. Finally, we show that the use of attention offers interpretability by identifying the most relevant correlations being tracked by the decoder. Enabling experimental validation of deep-circuit fault-tolerant algorithms and architectures (Bluvstein et al., arXiv:2506.20661, 2025), these results establish neural decoders as practical, versatile, and high-performance tools for quantum computing.

12 pages, 6 figures

References in corpus (47)

• Topological quantum memory
• Suppressing quantum errors by scaling a surface code logical qubit
• Logical quantum processor based on reconfigurable atom arrays
• Quantum error correction below the surface code threshold
• High-threshold and low-overhead fault-tolerant quantum memory
• Real-time quantum error correction beyond break-even
• Realization of an Error-Correcting Surface Code with Superconducting Qubits
• Quantum Low-Density Parity-Check Codes
• High-fidelity gates with mid-circuit erasure conversion in a metastable neutral atom qubit
• Efficient Algorithms for Maximum Likelihood Decoding in the Surface Code
• Erasure conversion for fault-tolerant quantum computing in alkaline earth Rydberg atom arrays
• Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
• A Neural Decoder for Topological Codes
• Erasure conversion in a high-fidelity Rydberg quantum simulator
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• Decoding Small Surface Codes with Feedforward Neural Networks
• Encoding a magic state with beyond break-even fidelity
• Sparse Blossom: correcting a million errors per core second with minimum-weight matching
• Deep Neural Network Probabilistic Decoder for Stabilizer Codes
• Matching and maximum likelihood decoding of a multi-round subsystem quantum error correction experiment
• Neural Belief-Propagation Decoders for Quantum Error-Correcting Codes
• Quantum error correction for the toric code using deep reinforcement learning
• Triangular color codes on trivalent graphs with flag qubits
• Deep neural decoders for near term fault-tolerant experiments
• Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network
• Improved decoding of circuit noise and fragile boundaries of tailored surface codes
• Advantages of versatile neural-network decoding for topological codes
• Neural-Network Decoders for Quantum Error Correction using Surface Codes:A Space Exploration of the Hardware Cost-Performance Trade-Offs
• Erasure qubits: Overcoming the $T_1$ limit in superconducting circuits
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Neural network decoder for topological color codes with circuit level noise
• Fault-Tolerant Weighted Union-Find Decoding on the Toric Code
• Architectural mechanisms of a universal fault-tolerant quantum computer
• A scalable and fast artificial neural network syndrome decoder for surface codes
• Reinforcement learning for optimal error correction of toric codes
• Neural Network Decoders for Large-Distance 2D Toric Codes
• A real-time, scalable, fast and highly resource efficient decoder for a quantum computer
• Deep Q-learning decoder for depolarizing noise on the toric code
• Techniques for combining fast local decoders with global decoders under circuit-level noise
• Low-Overhead Transversal Fault Tolerance for Universal Quantum Computation
• Symmetries for a High Level Neural Decoder on the Toric Code
• Constant-Overhead Fault-Tolerant Bell-Pair Distillation using High-Rate Codes
• Field-Programmable Gate Array Architecture for Deep Learning: Survey & Future Directions
• Data-driven decoding of quantum error correcting codes using graph neural networks
• Neural network decoder for near-term surface-code experiments
• Leveraging Qubit Loss Detection in Fault Tolerant Quantum Algorithms
• Decoding across transversal Clifford gates in the surface code