Low-Rank Bottleneck in Multi-head Attention Models

Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar. Low-Rank Bottleneck in Multi-head Attention Models. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Volume 119 of Proceedings of Machine Learning Research, pages 864-873, PMLR, 2020. [doi]

Abstract

Abstract is missing.