Deep learning algorithms are responsible for a technological revolution in a variety of tasks
including image recognition or Go playing. Yet, why they work is not understood. Ultimately …

With a goal of understanding what drives generalization in deep networks, we consider
several recently suggested explanations, including norm-based control, sharpness and …

Current methods for training robust networks lead to a drop in test accuracy, which has led
prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning …

Deep neural networks are notorious for being sensitive to small well-chosen perturbations,
and estimating the regularity of such architectures is of utmost importance for safe and …

We consider neural networks with a single hidden layer and non-decreasing positively
homogeneous activation functions like the rectified linear units. By letting the number of …

With the increase in available data parallel machine learning has become an increasingly
pressing problem. In this paper we present the first parallel stochastic gradient descent …

This book addresses some theoretical aspects of semisupervised learning (SSL). The book
is organized as a collection of different contributions of authors who are experts on this topic …

We present a new algorithm for a robust family of Earth Mover's Distances-EMDs with
thresholded ground distances. The algorithm transforms the flow-network of the EMD so that …

Given two probability measures, P and Q defined on a measurable space, S, the integral
probability metric (IPM) is defined as F (P, Q)=\sup\left {\left | S f\, d PS f\, d Q\right |\,:\, f ∈ …

Wasserstein distributionally robust optimization (DRO) aims to find robust and generalizable
solutions by hedging against data perturbations in Wasserstein distance. Despite its recent …