DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training.
Aochuan ChenYimeng ZhangJinghan JiaJames DiffenderferKonstantinos ParasyrisJiancheng LiuYihua ZhangZheng ZhangBhavya KailkhuraSijia LiuPublished in: ICLR (2024)
Keyphrases
- computational model
- data sets
- optimization model
- test data
- probabilistic model
- information retrieval
- response surface
- linear model
- formal model
- mathematical model
- bayesian networks
- high level
- test set
- input data
- optimization problems
- prior knowledge
- conceptual model
- artificial neural networks
- constrained optimization
- structured prediction
- genetic algorithm