QIBONN: A Quantum-Inspired Bilevel Optimizer for Neural Networks on Tabular Classification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chumpitaz-Flores, Pedro, Duong, My, Mao, Ying, Hua, Kaixun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912703972376576
author Chumpitaz-Flores, Pedro
Duong, My
Mao, Ying
Hua, Kaixun
author_facet Chumpitaz-Flores, Pedro
Duong, My
Mao, Ying
Hua, Kaixun
contents Hyperparameter optimization (HPO) for neural networks on tabular data is critical to a wide range of applications, yet it remains challenging due to large, non-convex search spaces and the cost of exhaustive tuning. We introduce the Quantum-Inspired Bilevel Optimizer for Neural Networks (QIBONN), a bilevel framework that encodes feature selection, architectural hyperparameters, and regularization in a unified qubit-based representation. By combining deterministic quantum-inspired rotations with stochastic qubit mutations guided by a global attractor, QIBONN balances exploration and exploitation under a fixed evaluation budget. We conduct systematic experiments under single-qubit bit-flip noise (0.1\%--1\%) emulated by an IBM-Q backend. Results on 13 real-world datasets indicate that QIBONN is competitive with established methods, including classical tree-based methods and both classical/quantum-inspired HPO algorithms under the same tuning budget.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08940
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QIBONN: A Quantum-Inspired Bilevel Optimizer for Neural Networks on Tabular Classification
Chumpitaz-Flores, Pedro
Duong, My
Mao, Ying
Hua, Kaixun
Machine Learning
Quantum Physics
Hyperparameter optimization (HPO) for neural networks on tabular data is critical to a wide range of applications, yet it remains challenging due to large, non-convex search spaces and the cost of exhaustive tuning. We introduce the Quantum-Inspired Bilevel Optimizer for Neural Networks (QIBONN), a bilevel framework that encodes feature selection, architectural hyperparameters, and regularization in a unified qubit-based representation. By combining deterministic quantum-inspired rotations with stochastic qubit mutations guided by a global attractor, QIBONN balances exploration and exploitation under a fixed evaluation budget. We conduct systematic experiments under single-qubit bit-flip noise (0.1\%--1\%) emulated by an IBM-Q backend. Results on 13 real-world datasets indicate that QIBONN is competitive with established methods, including classical tree-based methods and both classical/quantum-inspired HPO algorithms under the same tuning budget.
title QIBONN: A Quantum-Inspired Bilevel Optimizer for Neural Networks on Tabular Classification
topic Machine Learning
Quantum Physics
url https://arxiv.org/abs/2511.08940