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

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 hyper-parameters, 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.

• Publication year

  2025

• Venue

  BigData Congress [Services Society]

• Publication date

  2025-11-12

• Fields of study

  Physics, Computer Science

• Identifiers
  DOI 10.1109/BigData66926.2025.11401529arXiv 2511.08940
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Research on support vector machine optimization based on improved quantum genetic algorithm

  2023cited by this paper
• Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Models

  2023cited by this paper
• Music sentiment classification based on an optimized CNN-RF-QPSO model

  2023cited by this paper
• Predicting xylose yield from prehydrolysis of hardwoods: A machine learning approach

  2022cited by this paper
• Hybrid quantum ResNet for car classification and its hyperparameter optimization

  2022cited by this paper
• An Empirical Study of the Impact of Hyperparameter Tuning and Model Optimization on the Performance Properties of Deep Neural Networks

  2022cited by this paper
• Tabular Data: Deep Learning is Not All You Need

  2021cited by this paper
• Deep Neural Networks and Tabular Data: A Survey

  2021cited by this paper
• A review on genetic algorithm: past, present, and future

  2020cited by this paper
• Automatic tuning of hyperparameters using Bayesian optimization

  2020cited by this paper
• Survey of Swarm Intelligence Algorithms

  2020cited by this paper
• Hyperparameter Tuning using Quantum Genetic Algorithms

  2019cited by this paper
• Particle Swarm Optimization

  2019cited by this paper
• Tabular Benchmarks for Joint Architecture and Hyperparameter Optimization

  2019cited by this paper
• Quantum inspired high dimensional hyperparameter optimization of machine learning model

  2017cited by this paper
• CMA-ES for Hyperparameter Optimization of Deep Neural Networks

  2016cited by this paper
• Quantum Boltzmann Machine

  2016cited by this paper
• Random Search for Hyper-Parameter Optimization

  2012cited by this paper
• Quantum-inspired evolutionary algorithms: a survey and empirical study

  2011cited by this paper
• Algorithms for Hyper-Parameter Optimization

  2011cited by this paper
• Neural networks letter: Quantum inspired PSO for the optimization of simultaneous recurrent neural networks as MIMO learning systems

  2010cited by this paper
• Particle swarm optimization with particles having quantum behavior

  2004cited by this paper
• A quantum particle swarm optimization

  2004cited by this paper
• Quantum-inspired evolutionary algorithm for a class of combinatorial optimization

  2002cited by this paper
• Swarm Intelligence: From Natural to Artificial Systems

  2002cited by this paper

• No citing papers are available for this paper.