Classification methods based on k-logistic models

Logistic regression is a simple yet effective technique widely used in machine learning with applications spanning various scientific fields. In this paper, we introduce new logistic regression models based on the k-exponential function derived from k-statistical theory, which approaches the standard exponential function as its parameter k tends to zero. We propose models for both binary and multivariate classification, demonstrating that they extend traditional logistic regression while maintaining the same computational complexity as conventional logistic classifiers. Computational experiments on diverse benchmark data sets show that our k-logistic classifiers outperform standard logistic regression models in the vast majority of cases.