English

Laws of Learning Dynamics and the Core of Learners

Machine Learning 2026-02-06 v1 Artificial Intelligence Information Theory math.IT

Abstract

We formulate the fundamental laws governing learning dynamics, namely the conservation law and the decrease of total entropy. Within this framework, we introduce an entropy-based lifelong ensemble learning method. We evaluate its effectiveness by constructing an immunization mechanism to defend against transfer-based adversarial attacks on the CIFAR-10 dataset. Compared with a naive ensemble formed by simply averaging models specialized on clean and adversarial samples, the resulting logifold achieves higher accuracy in most test cases, with particularly large gains under strong perturbations.

Keywords

Cite

@article{arxiv.2602.05026,
  title  = {Laws of Learning Dynamics and the Core of Learners},
  author = {Inkee Jung and Siu Cheong Lau},
  journal= {arXiv preprint arXiv:2602.05026},
  year   = {2026}
}

Comments

14 pages, 5 figures