We introduce a novel classification framework, ZClassifier, that replaces conventional deterministic logits with diagonal Gaussian-distributed logits. Our method simultaneously addresses temperature scaling and manifold approximation by minimizing the KL divergence between the predicted Gaussian distributions and a unit isotropic Gaussian. This unifies uncertainty calibration and latent control in a principled probabilistic manner, enabling a natural interpretation of class confidence and geometric consistency. Experiments on CIFAR-10 and CIFAR-100 demonstrate that ZClassifier improves over softmax classifiers in robustness, calibration, and latent separation, with consistent benefits across small-scale and large-scale classification settings.
Cite
@article{arxiv.2507.10638,
title = {ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space},
author = {Shim Soon Yong},
journal= {arXiv preprint arXiv:2507.10638},
year = {2025}
}