conftrace_

gradient-based measure

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

parameter sensitivity (1) zero-shot cross-lingual transfer (1) model generalization (1) model pruning (1) neural network optimization (1) machine translation (1) knowledge distillation (1) gradient-based optimization (1)

Papers

The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains EMNLP 2022