Neural network decoder for near-term surface-code experiments

Abstract

Neural-network decoders can achieve a lower logical error rate compared to conventional decoders, like minimum-weight perfect matching, when decoding the surface code. Furthermore, these decoders require no prior information about the physical error rates, making them highly adaptable. In this study, we investigate the performance of such a decoder using both simulated and experimental data obtained from a transmon-qubit processor, focusing on small-distance surface codes. We first show that the neural network typically outperforms the matching decoder due to better handling errors leading to multiple correlated syndrome defects, such as $Y$ errors. When applied to the experimental data of [Google Quantum AI, Nature 614, 676 (2023)], the neural network decoder achieves logical error rates approximately $25\%$ lower than minimum-weight perfect matching, approaching the performance of a maximum-likelihood decoder. To demonstrate the flexibility of this decoder, we incorporate the soft information available in the analog readout of transmon qubits and evaluate the performance of this decoder in simulation using a symmetric Gaussian-noise model. Considering the soft information leads to an approximately $10\%$ lower logical error rate, depending on the probability of a measurement error. The good logical performance, flexibility, and computational efficiency make neural network decoders well-suited for near-term demonstrations of quantum memories.

15 pages, 8 figures, 1 table; Added/updated references, fixed typos, retrained some models to improve performance, and included a soft MWPM decoder comparison in Sec. III

References in corpus (25)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Surface codes: Towards practical large-scale quantum computation
• Suppressing quantum errors by scaling a surface code logical qubit
• Fault-tolerant quantum computation with high threshold in two dimensions
• High-fidelity preparation, gates, memory and readout of a trapped-ion quantum bit
• Real-time quantum error correction beyond break-even
• Exponential suppression of bit or phase flip errors with repetitive error correction
• Stim: a fast stabilizer circuit simulator
• Realization of an Error-Correcting Surface Code with Superconducting Qubits
• Low-distance Surface Codes under Realistic Quantum Noise
• Fault-tolerant operation of a logical qubit in a diamond quantum processor
• Efficient Algorithms for Maximum Likelihood Decoding in the Surface Code
• Logical-qubit operations in an error-detecting surface code
• Removing leakage-induced correlated errors in superconducting quantum error correction
• Matching and maximum likelihood decoding of a multi-round subsystem quantum error correction experiment
• Overcoming leakage in scalable quantum error correction
• Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network
• Calibrated decoders for experimental quantum error correction
• Improved decoding of circuit noise and fragile boundaries of tailored surface codes
• Neural-Network Decoders for Quantum Error Correction using Surface Codes:A Space Exploration of the Hardware Cost-Performance Trade-Offs
• Measurement-Induced State Transitions in a Superconducting Qubit: Within the Rotating Wave Approximation
• All-microwave leakage reduction units for quantum error correction with superconducting transmon qubits
• A scalable and fast artificial neural network syndrome decoder for surface codes
• Techniques for combining fast local decoders with global decoders under circuit-level noise
• Reducing the error rate of a superconducting logical qubit using analog readout information

Cited by in corpus (4)

• Data-driven decoding of quantum error correcting codes using graph neural networks
• Self-attention U-Net decoder for toric codes
• Neural Decoders for Universal Quantum Algorithms
• Soft information decoding with superconducting qubits