hardware algorithms error_correction machine_learning

Multi-Stage Mamba-Based Architecture for Fast and Scalable Superconducting Qubit Readout

Curator's Take

This article tackles one of the thorniest obstacles to fault‑tolerant quantum computing—slow, error‑prone readout of superconducting qubits—by introducing a multi‑stage discriminator built on the efficient Mamba sequence model. By halving the parameter count while pushing geometric‑mean fidelity past 0.91 and preserving performance at sub‑microsecond integration times, it outperforms prior feed‑forward neural approaches and directly translates into up to a 26 % reduction in logical error rates for surface‑code experiments. The work demonstrates how lightweight, end‑to‑end machine‑learning pipelines can be integrated into multiplexed readout chains, a step that could accelerate scaling of superconducting processors even though real‑world deployment will still need validation on larger qubit arrays.

— Mark Eatherly

Summary

Reliable qubit readout is a critical bottleneck toward fault-tolerant quantum computing (FTQC). In superconducting quantum processors, readout operations are both error-prone and high-latency. These challenges become more severe in frequency-multiplexed architectures, where signal crosstalk among neighboring qubits significantly degrades readout fidelity. Existing machine learning (ML)-based approaches rely on feed-forward neural networks (FNNs) that suffer from large parameter sizes and lack an end-to-end network that jointly addresses relaxation errors and discriminates qubit states. In this work, we present a multi-stage qubit state discriminator based on the Mamba model, which enables efficient sequence modeling with linear complexity. The first stage performs initial state discrimination, followed by a refinement stage that identifies and mitigates relaxation-induced errors. Our lightweight model achieves a geometric mean readout fidelity of 0.906, outperforming the best-reported state-of-the-art method while reducing parameter size by 49.6%; our optimal model further reaches 0.911. Both models remain robust across varying input trace lengths, maintaining a high fidelity of 0.893 at readout durations as short as 500 $ns$, achieving up to a 26% reduction in logical error rate over prior work in quantum error correction (QEC).