Hybrid Quantum-Classical Logistic Regression for Calibrated Classification of Pulsar Candidates

TL;DR

This paper evaluates hybrid quantum-classical logistic regression models for pulsar candidate classification, demonstrating that shallow angle encoding offers a good balance of calibration and discrimination, despite runtime challenges.

Contribution

It introduces and compares quantum logistic regression variants with classical models for pulsar data, highlighting the effectiveness of angle encoding at shallow depths.

Findings

Angle encoding yields the best performance among quantum variants.

Shallow angle-encoded models match classical baselines in discrimination and calibration.

Runtime remains a practical limitation for quantum simulations.

Abstract

Reliable pulsar candidate ranking requires probability estimates that are not only discriminative but also well calibrated. We evaluate hybrid quantum-calssical logistic regression on the imbalanced HTRU-2 dataset using three quantum feature encodings: angle encoding, amplitude encoding, and data re-uploading. The models are trained using analytic gradients and compared with classical baselines and a quantum support vector machine reference model under a paired-seed protocol. Evaluation combines rare-event discrimination, low-false-positive-rate recovery, probability calibration, and runtime analysis. Angle encoding gives the strongest performance among the quantum logistic regression variants. At shallow depth, the angle-encoded model remains close to the best classical baselines in discrimination and low-false-positive-rate recovery, while also giving the lowest calibration error at the benchmark configuration. Murphy decomposition shows that the angle-encoded model maintains low reliability error and high, stable resolution across circuit depths and training-set sizes. This means that its probability estimates preserve both calibration and meaningful separation between candidate groups. Data re-uploading is competitive at small depth but loses discrimination and resolution at larger depth in the present multi-qubit implementation, while amplitude encoding remains weaker across dataset sizes. Shallow angle-encoded quantum logistic regression therefore gives the best balance among the tested quantum logistic models, although simulation runtime remains a practical limitation.