Skip to content
conftrace_

embedding scaling

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

column-wise clipping (1) relative positional embedding (1) universal transformer (1) large batch training (1) positional embedding (1) click-through rate prediction (1) systematic generalization (1) model training (1) hyperparameter tuning (1) neural network optimization (1)

Papers

CowClip: Reducing CTR Prediction Model Training Time from 12 Hours to 10 Minutes on 1 GPU AAAI 2023 The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers EMNLP 2021