Goel, G., Soltanolkotabi, M., & Bartlett, P. (2026). Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning.
Chicago Style (17th ed.) CitationGoel, Gautam, Mahdi Soltanolkotabi, and Peter Bartlett. Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning. 2026.
MLA (9th ed.) CitationGoel, Gautam, et al. Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning. 2026.
Warning: These citations may not always be 100% accurate.