As a powerful modelling method, piecewise linear neural networks (PWLNNs) have proven
successful in various fields, most recently in deep learning. To apply PWLNN methods, both …

In the past decade, deep learning became the prevalent methodology for predictive
modeling thanks to the remarkable accuracy of deep neural networks in tasks such as …

Floods have been among the costliest hydrometeorological hazards across the globe for
decades, and are expected to become even more frequent and cause larger devastating …

Vision transformers using self-attention or its proposed alternatives have demonstrated
promising results in many image related tasks. However, the underpinning inductive bias of …

We develop fast algorithms and robust software for convex optimization of two-layer neural
networks with ReLU activation functions. Our work leverages a convex re-formulation of the …

We describe the convex semi-infinite dual of the two-layer vector-output ReLU neural
network training problem. This semi-infinite dual admits a finite dimensional representation …

We develop an analytical framework to characterize the set of optimal ReLU neural networks
by reformulating the non-convex training problem as a convex program. We show that the …

The nonconvexity of the artificial neural network (ANN) training landscape brings
optimization difficulties. While the traditional back-propagation stochastic gradient descent …

Batch Normalization (BN) is a commonly used technique to accelerate and stabilize training
of deep neural networks. Despite its empirical success, a full theoretical understanding of …

In this paper, we study the optimality gap between two-layer ReLU networks regularized with
weight decay and their convex relaxations. We show that when the training data is random …