A scalable and real-time neural decoder for topological quantum codes

TL;DR

This paper presents AlphaQubit 2, a neural network decoder capable of real-time, high-accuracy quantum error correction for surface and color codes, enabling scalable fault-tolerant quantum computing.

Contribution

Introduction of AlphaQubit 2, a neural decoder that achieves near-optimal error rates with real-time performance for large-scale quantum codes under realistic noise.

Findings

Achieves near-optimal logical error rates for surface and color codes.

Decodes in under 1 microsecond per cycle on commercial hardware.

First real-time decoding of the color code to distance 9.

Abstract

Fault-tolerant quantum computing will require error rates far below those achievable with physical qubits. Quantum error correction (QEC) bridges this gap, but depends on decoders being simultaneously fast, accurate, and scalable. This combination of requirements remains unmet by a machine-learning decoder, nor by any decoder for promising resource-efficient codes such as the color code. Here we introduce AlphaQubit 2, a neural-network decoder that achieves near-optimal logical error rates for both surface and color codes at scale under realistic noise. For the color code, it is orders of magnitude faster than other high-accuracy decoders. We demonstrate real-time decoding faster than 1{\mu}s per cycle on commercial accelerators: for the surface code to distance 11, with better accuracy than leading real-time decoders; and the first real-time decoding of the color code to distance 9. These results support the practical application of a wider class of promising QEC codes, and establish a credible path towards high-accuracy, real-time neural decoding at the scales required for fault-tolerant quantum computation.