Deep neural networks are generally designed as a stack of differentiable layers, in which a
prediction is obtained only after running the full stack. Recently, some contributions have …

Most of existing statistical theories on deep neural networks have sample complexities
cursed by the data dimension and therefore cannot well explain the empirical success of …

Convolutional neural networks (CNNs) have been shown to achieve optimal approximation
and estimation error rates (in minimax sense) in several function classes. However, previous …

In the context of adversarial robustness, a single model does not usually have enough
power to defend against all possible adversarial attacks, and as a result, has sub-optimal …

Network traffic forecasting is an operational and management function that is critical for any
data network. It is even more important for IoT networks given the number of connected …

We study the problem of teaching multiple learners simultaneously in the nonparametric
iterative teaching setting, where the teacher iteratively provides examples to the learner for …

We derive a novel approximation error bound with explicit prefactor for Sobolev-regular
functions using deep convolutional neural networks (CNNs). The bound is non-asymptotic in …

In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the
teacher provides examples to the learner iteratively such that the learner can achieve fast …

We propose a constrained linear data-feature-mapping model as an interpretable
mathematical model for image classification using a convolutional neural network (CNN) …

We investigated the feature map inside deep neural networks (DNNs) by tracking the
transport map. We are interested in the role of depth--why do DNNs perform better than …