Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks

Tolga Ergen, Mert Pilanci

Keywords: Convex optimization, deep learning theory, path norm, group sparsity, polynomial-time training, ReLU networks, parallel architectures, global optimality, computational complexity

TL;DR: We introduce a convex analytic framework to unveil a hidden convex optimization landscape for training path regularized deep neural networks.

Abstract: Understanding the fundamental principles behind the success of deep neural networks is one of the most important open questions in the current literature. To this end, we study the training problem of deep neural networks and introduce an analytic approach to unveil hidden convexity in the optimization landscape. We consider a deep parallel ReLU network architecture, which also includes standard deep networks and ResNets as its special cases. We then show that pathwise regularized training problems can be represented as an exact convex optimization problem. We further prove that the equivalent convex problem is regularized via a group sparsity inducing norm. Thus, a path regularized parallel ReLU network can be viewed as a parsimonious convex model in high dimensions. More importantly, we show that the computational complexity required to globally optimize the equivalent convex problem is fully polynomial-time in feature dimension and number of samples. Therefore, we prove polynomial-time trainability of path regularized ReLU networks with global optimality guarantees. We also provide experiments corroborating our theory.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

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

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Optimization (eg, convex and non-convex optimization)