Learning to Grow Pretrained Models for Efficient Transformer Training.
Peihao WangRameswar PandaLucas Torroba HennigenPhilip GreengardLeonid KarlinskyRogério FerisDavid Daniel CoxZhangyang WangYoon KimPublished in: CoRR (2023)
Keyphrases
- structured prediction
- supervised learning
- online learning
- prior knowledge
- learning algorithm
- probabilistic model
- learned models
- statistical models
- unsupervised learning
- knowledge acquisition
- efficient learning
- learning models
- active learning
- learning process
- learning speed
- conditional random fields
- computer based training
- learning machines
- hidden variables
- learning scenarios
- learning problems
- generative model
- reinforcement learning