Machine-learned syndrome post-selection for reliable quantum error correction

2026-07-21

AI Summary

This work addresses the lack of efficient, decoder-agnostic post-selection methods in quantum error correction. It proposes a supervised learning strategy that relies solely on syndrome data to train a classifier distinguishing syndromes generated under high versus low noise conditions, outputting an abort score to discard error-prone circuit executions—without requiring logical error labels or code-specific likelihood calculations. This approach achieves, for the first time, decoder-independent machine learning–based post-selection, revealing a distinct post-selection phase transition in the surface code. It significantly reduces the conditional logical error rate in both numerical simulations and experiments on QuEra’s neutral-atom quantum processor. When combined with logical gap filtering, the resulting output fidelity surpasses that attainable by logical gap filtering alone.

Abstract

Quantum error correction can be enhanced by post-selecting out runs that are likely to produce a logical failure, but the most accurate measures for that require costly decoder-level information. We introduce a practical, decoder-agnostic post-selection method that learns directly from syndrome data. The method trains a supervised classifier to distinguish between syndromes from low- and high-noise regimes, and then uses the classifier's output as an abort score for new runs, without requiring logical-error labels, correction operators, or code-specific likelihood calculations. We validate the approach in three complementary settings: circuit-level simulations of the Gross bivariate-bicycle code, code-capacity simulations of the surface code, and experimental logical magic-state distillation data from the QuEra neutral-atom processor. In the Gross and surface codes, learned syndrome post-selection reduces the conditional logical error rate at a fixed acceptance rate, with performance comparable to syndrome-weight filtering. For the surface code, the learned classifier reveals a post-selection transition distinct from the conventional decoding threshold. In the experimental data, the machine-learning score outperforms syndrome-weight post-selection and, when combined with logical-gap filtering, improves the output fidelity beyond using the logical gap alone. These results show that syndrome-only learning provides a scalable and hardware-compatible route to improving the reliability of quantum error correction.

Problem

• quantum error correction
• syndrome post-selection
• machine learning
• decoder-agnostic
• logical error rate

Innovation

• syndrome post-selection
• quantum error correction
• machine learning
• decoder-agnostic
• logical error rate