A Unified Framework for Proximal Methods

Jihun Yun, Aurelie Lozano, Eunho Yang

Keywords: Stochastic Optimization, Deep Learning, Proximal Gradient Descent

Abstract: We study the training of regularized neural networks where the regularizer can be non-smooth and non-convex.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=jC5aqqhroB2