Low-Rank Bottleneck in Multi-head Attention Models.
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Browse the full ICML paper archive.
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Browse the full ICML paper archive.