@article{tokenstatisticstransformerlineartime, title = {Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction}, author = {Ziyang Wu and Tianjiao Ding and Yifu Lu and Druv Pai and Jingyuan Zhang and Weida Wang and Yaodong Yu and Yi Ma and Benjamin D. Haeffele}, year = {2024}, eprint = {2412.17810}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.17810v1}, }