Scalable Neural Network Decoders for Higher Dimensional Quantum Codes

Abstract

Machine learning has the potential to become an important tool in quantum error correction as it allows the decoder to adapt to the error distribution of a quantum chip. An additional motivation for using neural networks is the fact that they can be evaluated by dedicated hardware which is very fast and consumes little power. Machine learning has been previously applied to decode the surface code. However, these approaches are not scalable as the training has to be redone for every system size which becomes increasingly difficult. In this work the existence of local decoders for higher dimensional codes leads us to use a low-depth convolutional neural network to locally assign a likelihood of error on each qubit. For noiseless syndrome measurements, numerical simulations show that the decoder has a threshold of around $7.1\%$ when applied to the 4D toric code. When the syndrome measurements are noisy, the decoder performs better for larger code sizes when the error probability is low. We also give theoretical and numerical analysis to show how a convolutional neural network is different from the 1-nearest neighbor algorithm, which is a baseline machine learning method.

References in corpus (3)

• Understanding deep learning requires rethinking generalization
• Low-distance Surface Codes under Realistic Quantum Noise
• In-situ characterization of quantum devices with error correction

Cited by in corpus (36)

• Experimental quantum speed-up in reinforcement learning agents
• Optimizing Quantum Error Correction Codes with Reinforcement Learning
• Neural Belief-Propagation Decoders for Quantum Error-Correcting Codes
• Quantum error correction for the toric code using deep reinforcement learning
• Deep neural decoders for near term fault-tolerant experiments
• Comparing neural network based decoders for the surface code
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Cellular-automaton decoders with provable thresholds for topological codes
• Neural network decoder for topological color codes with circuit level noise
• Single-shot error correction of three-dimensional homological product codes
• Hamiltonian Learning for Quantum Error Correction
• Quantum Error Correction with the Semion Code
• Parallelized quantum error correction with fracton topological codes
• A scalable and fast artificial neural network syndrome decoder for surface codes
• Artificial Intelligence for Quantum Computing
• Cellular automaton decoders for topological quantum codes with noisy measurements and beyond
• Neural Network Decoders for Large-Distance 2D Toric Codes
• Deep Q-learning decoder for depolarizing noise on the toric code
• General framework for constructing fast and near-optimal machine-learning-based decoder of the topological stabilizer codes
• Techniques for combining fast local decoders with global decoders under circuit-level noise
• Efficient color code decoders in $d\ge 2$ dimensions from toric code decoders
• Renormalization group decoder for a four-dimensional toric code
• Numerical Implementation of Just-In-Time Decoding in Novel Lattice Slices Through the Three-Dimensional Surface Code
• Determination of the Semion Code Threshold using Neural Decoders
• Tensor Network Decoding Beyond 2D
• Data-driven decoding of quantum error correcting codes using graph neural networks
• On maximum-likelihood decoding with circuit-level errors
• Concatenation Schemes for Topological Fault-tolerant Quantum Error Correction
• Improved Belief Propagation Decoding Algorithms for Surface Codes
• Error-rate-agnostic decoding of topological stabilizer codes
• Low-overhead quantum error correction codes with a cyclic topology
• Single-shot and measurement-based quantum error correction via fault complexes
• Enhancing Quantum Memory Lifetime with Measurement-Free Local Error Correction and Reinforcement Learning
• On the energy barrier of hypergraph product codes
• Self-attention U-Net decoder for toric codes
• Stabilization of symmetry-protected long-range entanglement in stochastic quantum circuits