Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
Page 1 Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two …

Multilayer neural networks are among the most powerful models in machine learning, yet the
fundamental reasons for this success defy mathematical understanding. Learning a neural …

In this paper, we study the problem of learning a shallow artificial neural network that best
fits a training data set. We study this problem in the over-parameterized regime where the …

Deep neural networks (DNNs) generate much richer function spaces than shallow networks.
Since the function spaces induced by shallow networks have several approximation …

Many machine learning models are vulnerable to adversarial attacks; for example, adding
adversarial perturbations that are imperceptible to humans can often make machine …

Common recurrent neural architectures scale poorly due to the intrinsic difficulty in
parallelizing their state computations. In this work, we propose the Simple Recurrent Unit …

The lack of interpretability remains a key barrier to the adoption of deep models in many
applications. In this work, we explicitly regularize deep models so human users might step …

In this paper, we consider regression problems with one-hidden-layer neural networks
(1NNs). We distill some properties of activation functions that lead to local strong convexity …

We consider the problem of learning a one-hidden-layer neural network: we assume the
input $ x\in\mathbb {R}^ d $ is from Gaussian distribution and the label $ y= a^\top\sigma …

How can neural networks such as ResNet\emph {efficiently} learn CIFAR-10 with test
accuracy more than $96\% $, while other methods, especially kernel methods, fall relatively …