Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network

Abstract

Quantum error-correction is a prerequisite for reliable quantum computation. Towards this goal, we present a recurrent, transformer-based neural network which learns to decode the surface code, the leading quantum error-correction code. Our decoder outperforms state-of-the-art algorithmic decoders on real-world data from Google's Sycamore quantum processor for distance 3 and 5 surface codes. On distances up to 11, the decoder maintains its advantage on simulated data with realistic noise including cross-talk, leakage, and analog readout signals, and sustains its accuracy far beyond the 25 cycles it was trained on. Our work illustrates the ability of machine learning to go beyond human-designed algorithms by learning from data directly, highlighting machine learning as a strong contender for decoding in quantum computers.

References in corpus (64)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Fault-tolerant quantum computation by anyons
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Surface codes: Towards practical large-scale quantum computation
• Cavity quantum electrodynamics for superconducting electrical circuits: an architecture for quantum computation
• LoRA: Low-Rank Adaptation of Large Language Models
• Quantum Annealing in the Transverse Ising Model
• Topological quantum memory
• Suppressing quantum errors by scaling a surface code logical qubit
• Logical quantum processor based on reconfigurable atom arrays
• How to factor 2048 bit RSA integers in 8 hours using 20 million noisy qubits
• Realizing Repeated Quantum Error Correction in a Distance-Three Surface Code
• Quantum error correction in a solid-state hybrid spin register
• Approaching Unit Visibility for Control of a Superconducting Qubit with Dispersive Readout
• Quantum advantage in learning from experiments
• Fast Scalable State Measurement with Superconducting Qubits
• 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
• Magic state distillation with low overhead
• Realization of an Error-Correcting Surface Code with Superconducting Qubits
• The XZZX Surface Code
• Fault-tolerant quantum computation with long-range correlated noise
• Efficient Algorithms for Maximum Likelihood Decoding in the Surface Code
• Measurement-induced state transitions in a superconducting qubit: Beyond the rotating wave approximation
• Towards practical classical processing for the surface code
• A Neural Decoder for Topological Codes
• Optimal Resources for Topological 2D Stabilizer Codes: Comparative Study
• Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
• Suppression of crosstalk in superconducting qubits using dynamical decoupling
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• Removing leakage-induced correlated errors in superconducting quantum error correction
• Encoding a magic state with beyond break-even fidelity
• Deep Neural Network Probabilistic Decoder for Stabilizer Codes
• Matching and maximum likelihood decoding of a multi-round subsystem quantum error correction experiment
• Density-matrix simulation of small surface codes under current and projected experimental noise
• Quantum error correction for the toric code using deep reinforcement learning
• Overcoming leakage in scalable quantum error correction
• A Fault-Tolerant Honeycomb Memory
• Deep neural decoders for near term fault-tolerant experiments
• 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
• Advantages of versatile neural-network decoding for topological codes
• Parallel window decoding enables scalable fault tolerant quantum computation
• Comparing neural network based decoders for the surface code
• Measurement-Induced State Transitions in a Superconducting Qubit: Within the Rotating Wave Approximation
• Understanding the effects of leakage in superconducting quantum error detection circuits
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Neural network decoder for topological color codes with circuit level noise
• Logical blocks for fault-tolerant topological quantum computation
• Quantum teleportation of physical qubits into logical code-spaces
• A scalable and fast artificial neural network syndrome decoder for surface codes
• Neural Network Decoders for Large-Distance 2D Toric Codes
• Deep Q-learning decoder for depolarizing noise on the toric code
• Techniques for combining fast local decoders with global decoders under circuit-level noise
• Pipelined correlated minimum weight perfect matching of the surface code
• Fault-tolerant Post-Selection for Low Overhead Magic State Preparation
• Symmetries for a High Level Neural Decoder on the Toric Code
• Performance enhancement of surface codes via recursive MWPM decoding
• Convolutional neural network based decoders for surface codes
• Artificial Neural Network Syndrome Decoding on IBM Quantum Processors
• A Scalable, Fast and Programmable Neural Decoder for Fault-Tolerant Quantum Computation Using Surface Codes
• Transformer-QEC: Quantum Error Correction Code Decoding with Transferable Transformers

Cited by in corpus (25)

• Quantum error correction below the surface code threshold
• Scaling and logic in the color code on a superconducting quantum processor
• Artificial Intelligence for Quantum Computing
• Beyond NISQ: The Megaquop Machine
• Tensor networks for quantum computing
• Data-driven decoding of quantum error correcting codes using graph neural networks
• Bridging Paradigms: Designing for HPC-Quantum Convergence
• Neural network decoder for near-term surface-code experiments
• Scalable noise characterization of syndrome-extraction circuits with averaged circuit eigenvalue sampling
• Leveraging Qubit Loss Detection in Fault Tolerant Quantum Algorithms
• Compiling the surface code to crossbar spin qubit architectures
• Introduction to Quantum Error Correction with Stabilizer Codes
• Harnessing Quantum Computing for Energy Materials: Opportunities and Challenges
• Thresholds for post-selected quantum error correction from statistical mechanics
• Self-attention U-Net decoder for toric codes
• Artificial intelligence for representing and characterizing quantum systems
• Optimal number of stabilizer measurement rounds in an idling surface code patch
• Noise tolerance via reinforcement: Learning a reinforced quantum dynamics
• Exact and Efficient Stabilizer Simulation of Thermal-Relaxation Noise for Quantum Error Correction
• On the interpretability of neural network decoders
• A Model Context Protocol Server for Quantum Execution in Hybrid Quantum-HPC Environments
• Disambiguating Pauli noise in quantum computers
• Automated discovery and optimization of autonomous quantum error correction codes for a general open quantum system
• Neural Decoders for Universal Quantum Algorithms
• Soft information decoding with superconducting qubits