@misc{makkuva2024attention, title={Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains}, author={Ashok Vardhan Makkuva and Marco Bondaschi and Adway Girish and Alliot Nagle and Martin Jaggi and Hyeji Kim and Michael Gastpar}, year={2024}, eprint={2402.04161}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2402.04161} }