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

TL;DR

QIBONN is a novel quantum-inspired bilevel optimizer for neural network hyperparameter tuning on tabular data, balancing exploration and exploitation within fixed evaluation budgets, and demonstrating competitive performance on real datasets.

Contribution

It introduces a unified qubit-based framework for hyperparameter optimization, combining quantum-inspired rotations and stochastic mutations for efficient search.

Findings

QIBONN performs competitively with classical and quantum-inspired methods.

It effectively balances exploration and exploitation under limited evaluation budgets.

Systematic experiments on 13 datasets validate its robustness and efficiency.

Abstract

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.