Machine Learning Decoding of Circuit-Level Noise for Bivariate Bicycle Codes
read the original abstract
Fault-tolerant quantum computers will depend crucially on the performance of the classical decoding algorithm which takes in the results of measurements and outputs corrections to the errors inferred to have occurred. Machine learning models have shown great promise as decoders for the surface code; however, this promise has not yet been substantiated for the more challenging task of decoding quantum low-density parity-check (QLDPC) codes. In this paper, we present a recurrent, transformer-based neural network designed to decode circuit-level noise on Bivariate Bicycle (BB) codes. For the $[[72,12,6]]$ BB code, at a physical error rate of $p=0.1\%$, our model achieves logical error rates almost $5$ times lower than belief propagation with ordered statistics decoding (BP-OSD), and roughly $5$ times larger than a most-likely error decoder. Moreover, while BP-OSD has a wide distribution of runtimes with significant outliers, our model has a consistent runtime and is an order-of-magnitude faster than the worst-case times from a benchmark BP-OSD implementation. On the $[[144,12,12]]$ BB code, our model obtains worse logical error rates but maintains the speed advantage. These results provide initial evidence that machine learning decoders can out-perform conventional decoders on small QLDPC codes, but suggest more complex architectures and/or training procedures are necessary to scale to larger code sizes.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation
Neural decoder for quantum LDPC codes achieves ~10^{-10} logical error at 0.1% physical error with 17x improvement and high throughput, enabling practical fault tolerance at modest code sizes.
-
Symmetry-enriched topological order and quasifractonic behavior in $\mathbb{Z}_N$ stabilizer codes
Z_N bivariate-bicycle codes have essential topological properties determined by their Z_p prime-factor counterparts, enabling generalization of algebraic-geometric methods to anyon fusion rules and resolution of quasi...
-
Approximating optimal decoding of quantum LDPC codes with narrow frontiers
The Frontier decoder approximates optimal quantum LDPC decoding via narrow-frontier dynamic programming, achieving near-optimal thresholds for surface and color codes plus state-of-the-art circuit-level performance wi...
-
Towards Ultra-High-Rate Quantum Error Correction with Reconfigurable Atom Arrays
A family of quantum LDPC codes with encoding rates exceeding 1/2 achieves logical error rates of 10^{-13} per round on atom arrays under 0.1% circuit noise using hierarchical decoding.
-
AI-Enabled Decoding of Qubit Loss for Quantum Error-Correcting Codes
An STGNN decoder outperforms standard and delayed-erasure MWPM algorithms in logical accuracy while recovering more than 90% of qubit loss locations after ten measurement rounds.
-
Accelerating BP-based decoders for QLDPC Codes with Local Syndrome-Based Preprocessing
Local syndrome-based preprocessing accelerates BP decoders for quantum LDPC codes, delivering up to 10x speedup on the [[144,12,12]] code while maintaining or improving logical error rates.
-
Fully convolutional 3D neural network decoders for surface codes with syndrome circuit noise
A 3D convolutional neural network decoder for surface codes with circuit noise generalizes to distance-97 codes with thresholds up to 0.7% depolarizing noise and improved latency over MWPM above distance 33.
-
Untangling QLDPC Codes with Biased Noise Ancilla
Biased-noise ancillas (phase flips only) in bicycle bivariate and cyclic hypergraph product QLDPC codes increase effective fault distance, reduce short loops, and improve logical error rate by nearly 10x at 2e-3 circu...
-
Maximum Likelihood Decoding of Quantum Error Correction Codes
A topical review unifying statistical mechanics, tensor network, and AI approaches to approximate maximum likelihood decoding for quantum error correction codes.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.