A neural decoder that identifies quantum errors more accurately than hand-designed methods
A neural decoder that identifies quantum errors more accurately than hand-designed methods is graded peer reviewed on whataifound.org, with the AI's role graded ai-led.
A transformer trained on Google's Sycamore surface-code data cut decoding errors by 6% against tensor-network decoding and 30% against correlated matching, the best reported accuracy at the time.
- Verification
- Peer reviewed
- Autonomy
- AI-led
- Lab
- Google DeepMind / Google Quantum AI
- Model
- AlphaQubit
- Field
- Physics
- Date
- 2024-11-20
What was found
A quantum error-correcting code produces a stream of syndrome measurements; a decoder has to infer from them which errors actually occurred. Hand-designed decoders assume a simplified noise model, whereas AlphaQubit is a transformer trained first on simulated data and then fine-tuned on hundreds of millions of real syndrome samples from Sycamore, so it can learn the device's actual correlated noise, leakage and crosstalk. It beat both the accuracy-oriented tensor-network decoder and the fast matching decoder, and held up in simulation to distance-11 codes. Published in Nature.
Novelty check
Machine-learning decoders had been proposed for years but had not beaten the best classical decoders on real hardware data at scale. The result is a decoder that does, on a specific processor.
Caveats
Accuracy, not speed: AlphaQubit is far slower than matching decoders and does not run inside the real-time budget a fault-tolerant machine needs, which the paper states. It is trained per device on that device's data, so it does not transfer for free. Scaling behaviour beyond the tested code distances is open. This improves a component of error correction; it does not itself demonstrate a fault-tolerant computation.
Sources
How this is graded
whataifound.org grades every entry on two axes: verification (how solid the result is, from a machine-checked proof down to refuted) and autonomy (how much the AI did versus its human collaborators). This finding is peer reviewed and ai-led. Full definitions are in the methodology.
Cite this entry
whataifound.org (2024). A neural decoder that identifies quantum errors more accurately than hand-designed methods. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2024-11-20-alphaqubit