From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers.
Krzysztof Choromanski, Han Lin, Haoxian Chen, Tianyi Zhang, Arijit Sehanobish, Valerii Likhosherstov, Jack Parker-Holder, Tams Sarls, Adrian Weller, Thomas Weingarten
Browse the full ICML paper archive.