Partial differential equation regularization for supervised machine learning
This is an incremental contribution that reframes existing regularization techniques in machine learning for researchers and practitioners.
The paper provides an overview of supervised machine learning for regression and classification, covering topics like kernel methods, deep learning, and generalization bounds, and reframes implicit regularization methods such as data augmentation and adversarial training as explicit gradient regularization.
This article is an overview of supervised machine learning problems for regression and classification. Topics include: kernel methods, training by stochastic gradient descent, deep learning architecture, losses for classification, statistical learning theory, and dimension independent generalization bounds. Implicit regularization in deep learning examples are presented, including data augmentation, adversarial training, and additive noise. These methods are reframed as explicit gradient regularization.