arXiv Machine Learning By Ran Miao, Rui Luo, Xiaohan Shan, Xiaoming Sun

QAdapt: A Noise-Adaptive Neural Pre-Decoding Framework for Quantum Error Correction

Read the original on arXiv Machine Learning →

arXiv:2607. 28422v1 Announce Type: new Abstract: Fault-tolerant quantum computing (FTQC) relies on quantum error correction to suppress physical errors and preserve logical information at scale.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Sep 4

Learning to Concatenate Quantum Codes

The paper proposes a hybrid, learning‑based strategy for selecting quantum error‑correcting codes at each concatenation level. By estimating the effective noise channel after each level, the method chooses small, non‑additive encoders when the noise has structure and switches to standard codes as the noise becomes uniform. Simulations show that this adaptive approach can achieve a target logical error rate with up to two orders of magnitude fewer qubits than using stabilizer codes alone for strongly structured noise.

By Nico Meyer, Christopher Mutschler, Dominik Seu{\ss}, Andreas Maier, Daniel D. Scherer
arXiv AI
Jul 14

MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery

arXiv:2607. 10707v1 Announce Type: cross Abstract: We propose a unified meta-decoding framework for quantum error correction that learns syndrome-to-recovery mappings across multiple stabilizer codes and noise settings, without requiring separate decoders for each configuration.

By Prashant Kumar Choudhary, Nouhaila Innan, Muhammad Shafique, Rajeev Singh
arXiv Machine Learning
Sep 3

Learning Encodings by Maximizing State Distinguishability: Variational Quantum Error Correction

The paper introduces a new objective function for designing quantum error correction codes that maximizes the distinguishability of quantum states after a noise channel. This approach, called variational quantum error correction (VarQEC), uses a distinguishability loss function as a machine learning objective to discover encoding circuits tailored to specific noise characteristics. The authors demonstrate that VarQEC produces resource‑efficient codes that outperform standard codes and provide proof‑of‑concept experiments on IBM and IQM hardware.

By Nico Meyer, Christopher Mutschler, Andreas Maier, Daniel D. Scherer