@article{optimizingattentionwithmirrordescent, title = {Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection}, author = {Aaron Alvarado Kristanto Julistiono and Davoud Ataee Tarzanagh and Navid Azizan}, year = {2024}, eprint = {2410.14581}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.14581v1}, }