LU, Yishun; ARMOUR, Wesley. Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 29, p. 24115–24123, 2026. DOI: 10.1609/aaai.v40i29.39590. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39590. Acesso em: 27 may. 2026.