Saved in:
Bibliographic Details
Main Authors: Uotila, Valter, Mehtola, Väinö, Salmenperä, Ilmo, Zhao, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.04243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908789781823488
author Uotila, Valter
Mehtola, Väinö
Salmenperä, Ilmo
Zhao, Bo
author_facet Uotila, Valter
Mehtola, Väinö
Salmenperä, Ilmo
Zhao, Bo
contents Symmetry is a strong inductive bias in geometric deep learning and its quantum counterpart, and has attracted increasing attention for improving the trainability of QML models. Yet incorporating symmetries into quantum machine learning (QML) ansatzes is not free: symmetrization often adds gates and constrains the circuits. To understand these effects, we present Twirlator, which is an automated pipeline that symmetrizes parameterized QML ansatzes and quantifies the trade-offs as the amount of symmetry increases. Twirlator models partial symmetries by the size of a subgroup of the symmetric group, enabling analysis between the ``no symmetry'' and ``full symmetry'' extremes. Across 19 common ansatz patterns, Twirlator symmetrizes circuits with respect to any subgroup of $S_n$ and measures (1) generator drift, (2) circuit overhead (depth and size), and (3) expressibility and entangling capability. The experimental evaluation focuses on subgroups of $S_4$ and $S_5$. Twirlator reveals that larger subgroups typically increase circuit overhead, reduce expressibility, and often increase entangling capability. The pipeline and results provide practical guidance for selecting ansatz patterns and symmetry levels that balance hardware cost and model performance in symmetry-aware QML applications.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04243
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Twirlator: A Pipeline for Analyzing Subgroup Symmetry Effects in Quantum Machine Learning Ansatzes
Uotila, Valter
Mehtola, Väinö
Salmenperä, Ilmo
Zhao, Bo
Quantum Physics
Machine Learning
Symmetry is a strong inductive bias in geometric deep learning and its quantum counterpart, and has attracted increasing attention for improving the trainability of QML models. Yet incorporating symmetries into quantum machine learning (QML) ansatzes is not free: symmetrization often adds gates and constrains the circuits. To understand these effects, we present Twirlator, which is an automated pipeline that symmetrizes parameterized QML ansatzes and quantifies the trade-offs as the amount of symmetry increases. Twirlator models partial symmetries by the size of a subgroup of the symmetric group, enabling analysis between the ``no symmetry'' and ``full symmetry'' extremes. Across 19 common ansatz patterns, Twirlator symmetrizes circuits with respect to any subgroup of $S_n$ and measures (1) generator drift, (2) circuit overhead (depth and size), and (3) expressibility and entangling capability. The experimental evaluation focuses on subgroups of $S_4$ and $S_5$. Twirlator reveals that larger subgroups typically increase circuit overhead, reduce expressibility, and often increase entangling capability. The pipeline and results provide practical guidance for selecting ansatz patterns and symmetry levels that balance hardware cost and model performance in symmetry-aware QML applications.
title Twirlator: A Pipeline for Analyzing Subgroup Symmetry Effects in Quantum Machine Learning Ansatzes
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2511.04243