Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization

2021 (modified: 27 May 2022)EMNLP (Findings) 2021Readers: Everyone

Abstract: Akhil Kedia, Sai Chetan Chinthakindi, Wonho Ryu. Findings of the Association for Computational Linguistics: EMNLP 2021. 2021.

0 Replies