On the Implicit Bias in Deep-Learning Algorithms
share
Gradient-based deep-learning algorithms exhibit remarkable performance in practice, but it is not well-understood why they are able to generalize despite having more parameters than training examples. It is believed that implicit bias is a key factor in their ability to generalize, and hence it has been widely studied in recent years. In this short survey, we explain the notion of implicit bias, review main results and discuss their implications.
READ FULL TEXT