Paper ID: 2302.10298

Quantum Machine Learning hyperparameter search

S. Consul-Pacareu, R. Montaño, Kevin Rodriguez-Fernandez, Àlex Corretgé, Esteve Vilella-Moreno, Daniel Casado-Faulí, Parfait Atchade-Adelomou

This paper presents a quantum-based Fourier-regression approach for machine learning hyperparameter optimization applied to a benchmark of models trained on a dataset related to a forecast problem in the airline industry. Our approach utilizes the Fourier series method to represent the hyperparameter search space, which is then optimized using quantum algorithms to find the optimal set of hyperparameters for a given machine learning model. Our study evaluates the proposed method on a benchmark of models trained to predict a forecast problem in the airline industry using a standard HyperParameter Optimizer (HPO). The results show that our approach outperforms traditional hyperparameter optimization methods in terms of accuracy and convergence speed for the given search space. Our study provides a new direction for future research in quantum-based machine learning hyperparameter optimization.

Submitted: Feb 20, 2023