Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Masta, Apoorv Kumar, Ganguly, Srinjoy, Devendrababu, Shalini, Riaz, Farina, Rana, Rajib, Schuller, Björn
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.27377
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914429730291712
author Masta, Apoorv Kumar
Ganguly, Srinjoy
Devendrababu, Shalini
Riaz, Farina
Rana, Rajib
Schuller, Björn
author_facet Masta, Apoorv Kumar
Ganguly, Srinjoy
Devendrababu, Shalini
Riaz, Farina
Rana, Rajib
Schuller, Björn
contents Quantum machine learning has faced growing scrutiny over its practical advantages compared to classical approaches, particularly following dequantization results and large scale benchmarking studies that have challenged earlier optimistic claims. This work presents a systematic empirical evaluation of non unitary quantum machine learning implemented via the Linear Combination of Unitaries framework within hybrid quantum classical neural networks. Across more than 570 experiments spanning four domains digit classification MNIST, agricultural disease detection PlantVillage, molecular property regression QM9, and medical histopathology PathMNIST non unitary quantum layers are benchmarked against structurally identical unitary baselines. Consistent performance improvements are observed across all domains, with gains ranging from +0.2 percentage to +5.8 percentage depending on dataset complexity and qubit count. A particularly notable finding is a Fisher efficiency transition in medical imaging tasks, where parameter efficiency shifts from negative to positive as qubit count increases from 10 to 12, indicating a threshold dependent efficiency regime. Additionally, non unitary IQP circuit variants reach or exceed classical baselines at 10 qubits on CIFAR 10, demonstrating that circuits with established complexity theoretic hardness guarantees remain compatible with competitive learning performance under the LCU framework. These results offer a large scale, evidence based characterisation of the conditions under which non unitary QML yields measurable empirical benefits in near term settings.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27377
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Non-Unitary Quantum Machine Learning: Fisher Efficiency Transitions from Distributed Quantum Expressivity
Masta, Apoorv Kumar
Ganguly, Srinjoy
Devendrababu, Shalini
Riaz, Farina
Rana, Rajib
Schuller, Björn
Quantum Physics
Applied Physics
Quantum machine learning has faced growing scrutiny over its practical advantages compared to classical approaches, particularly following dequantization results and large scale benchmarking studies that have challenged earlier optimistic claims. This work presents a systematic empirical evaluation of non unitary quantum machine learning implemented via the Linear Combination of Unitaries framework within hybrid quantum classical neural networks. Across more than 570 experiments spanning four domains digit classification MNIST, agricultural disease detection PlantVillage, molecular property regression QM9, and medical histopathology PathMNIST non unitary quantum layers are benchmarked against structurally identical unitary baselines. Consistent performance improvements are observed across all domains, with gains ranging from +0.2 percentage to +5.8 percentage depending on dataset complexity and qubit count. A particularly notable finding is a Fisher efficiency transition in medical imaging tasks, where parameter efficiency shifts from negative to positive as qubit count increases from 10 to 12, indicating a threshold dependent efficiency regime. Additionally, non unitary IQP circuit variants reach or exceed classical baselines at 10 qubits on CIFAR 10, demonstrating that circuits with established complexity theoretic hardness guarantees remain compatible with competitive learning performance under the LCU framework. These results offer a large scale, evidence based characterisation of the conditions under which non unitary QML yields measurable empirical benefits in near term settings.
title Non-Unitary Quantum Machine Learning: Fisher Efficiency Transitions from Distributed Quantum Expressivity
topic Quantum Physics
Applied Physics
url https://arxiv.org/abs/2603.27377