[1]
Lu, Y. and Armour, W. 2026. Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 29 (Mar. 2026), 24115–24123. DOI:https://doi.org/10.1609/aaai.v40i29.39590.