Model selection in hybrid quantum neural networks with applications to quantum transformer architectures
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911538029264896 |
|---|---|
| author | Wadhwa, Harsh Bhowmick, Rahul Raj, Naipunnya Sangle, Rajiv Bhat, Ruchira V. Sabapathy, Krishnakumar |
| author_facet | Wadhwa, Harsh Bhowmick, Rahul Raj, Naipunnya Sangle, Rajiv Bhat, Ruchira V. Sabapathy, Krishnakumar |
| contents | Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective configuration. To address this challenge, we develope the Quantum Bias-Expressivity Toolbox ($\texttt{QBET}$), a framework for evaluating quantum, classical, and hybrid transformer architectures. In this toolbox, we introduce lean metrics for Simplicity Bias ($\texttt{SB}$) and Expressivity ($\texttt{EXP}$), for comparing across various models, and extend the analysis of $\texttt{SB}$ to generative and multiclass-classification tasks. We show that $\texttt{QBET}$ enables efficient pre-screening of promising model variants obviating the need to execute complete training pipelines. In evaluations on transformer-based classification and generative tasks we employ a total of $18$ qubits for embeddings ($6$ qubits each for query, key, and value). We identify scenarios in which quantum self-attention variants surpass their classical counterparts by ranking the respective models according to the $\texttt{SB}$ metric and comparing their relative performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21749 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Model selection in hybrid quantum neural networks with applications to quantum transformer architectures Wadhwa, Harsh Bhowmick, Rahul Raj, Naipunnya Sangle, Rajiv Bhat, Ruchira V. Sabapathy, Krishnakumar Quantum Physics Machine Learning Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective configuration. To address this challenge, we develope the Quantum Bias-Expressivity Toolbox ($\texttt{QBET}$), a framework for evaluating quantum, classical, and hybrid transformer architectures. In this toolbox, we introduce lean metrics for Simplicity Bias ($\texttt{SB}$) and Expressivity ($\texttt{EXP}$), for comparing across various models, and extend the analysis of $\texttt{SB}$ to generative and multiclass-classification tasks. We show that $\texttt{QBET}$ enables efficient pre-screening of promising model variants obviating the need to execute complete training pipelines. In evaluations on transformer-based classification and generative tasks we employ a total of $18$ qubits for embeddings ($6$ qubits each for query, key, and value). We identify scenarios in which quantum self-attention variants surpass their classical counterparts by ranking the respective models according to the $\texttt{SB}$ metric and comparing their relative performance. |
| title | Model selection in hybrid quantum neural networks with applications to quantum transformer architectures |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2603.21749 |