Time-series based quantum state discrimination

TL;DR

This paper demonstrates that applying time-series machine learning models, specifically LSTM networks, to raw quantum measurement signals significantly improves state discrimination accuracy over traditional clustering methods, especially in boundary cases.

Contribution

The study introduces the use of sequence-aware models like LSTM for quantum state discrimination, outperforming clustering on integrated signals by leveraging temporal information.

Findings

LSTM models outperform clustering in classification accuracy.

Temporal features improve discrimination of boundary cases.

Sequence models better handle noisy and transient measurement signals.

Abstract

Accurate quantum state readout is crucial for error correction and algorithms, but measurement errors are detrimental. Readout fidelity is typically limited by a poor signal-to-noise ratio (SNR) and energy relaxation ($T_1$ decay), a significant problem for superconducting qubits. While most approaches classify results using clustering algorithms on integrated readout signals, these methods cannot distinguish a qubit that was initially in the ground state from one that decayed to it during measurement. We instead propose using machine learning (ML) on the raw, non-integrated analog signal. We apply time-series classification models, such as a long short-term memory (LSTM) network, to the full data trajectory. We find that our LSTM model, combined with filtering and feature engineering, consistently outperforms clustering. The largest improvements come from reclassifying points in the boundary regions between clusters. These points correspond to atypical measurement records, likely due to transient or noisy features lost during data integration. By retaining temporal information, sequence-aware models like LSTMs can better discriminate these trajectories, whereas clustering methods based on integrated values are more prone to misclassification.