Superiority of Multi-Head Attention: A Theoretical Study in Shallow Transformers in In-Context Linear Regression.
Yingqian Cui, Jie Ren, Pengfei He, Hui Liu, Jiliang Tang, Yue Xing
Browse the full AISTATS paper archive.
Yingqian Cui, Jie Ren, Pengfei He, Hui Liu, Jiliang Tang, Yue Xing
Browse the full AISTATS paper archive.