Implicit Regularization in Deep Learning
It addresses the problem of understanding generalization in deep learning for researchers, but it is incremental as it builds on existing theories without introducing a new paradigm.
The paper investigates implicit regularization from optimization methods as a key factor in the generalization and success of deep learning models, exploring how complexity measures and invariances can explain observed phenomena and evaluating them on learning tasks.
In an attempt to better understand generalization in deep learning, we study several possible explanations. We show that implicit regularization induced by the optimization method is playing a key role in generalization and success of deep learning models. Motivated by this view, we study how different complexity measures can ensure generalization and explain how optimization algorithms can implicitly regularize complexity measures. We empirically investigate the ability of these measures to explain different observed phenomena in deep learning. We further study the invariances in neural networks, suggest complexity measures and optimization algorithms that have similar invariances to those in neural networks and evaluate them on a number of learning tasks.