Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining.
Lu MiaoXiaolong LuoTianlong ChenWuyang ChenDong LiuZhangyang WangPublished in: ICLR (2022)
Keyphrases
- prior knowledge
- learning algorithm
- online learning
- reinforcement learning
- data sets
- unsupervised learning
- connectionist networks
- learning process
- learning analytics
- face recognition
- search space
- social networks
- active learning
- knowledge acquisition
- learning systems
- learning problems
- incremental learning
- recurrent networks