Deep learning has achieved tremendous success in recent years. In simple words, deep
learning uses the composition of many nonlinear functions to model the complex …

Deep learning's recent history has been one of achievement: from triumphing over humans
in the game of Go to world-leading performance in image classification, voice recognition …

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-
imbalance but the testing criterion requires good generalization on less frequent classes …

Generalization of deep networks has been of great interest in recent years, resulting in a
number of theoretically and empirically motivated complexity measures. However, most …

Recent works have cast some light on the mystery of why deep nets fit any data and
generalize despite being very overparametrized. This paper analyzes training and …

Despite the great empirical success of deep reinforcement learning, its theoretical
foundation is less well understood. In this work, we make the first attempt to theoretically …

Several works have proposed Simplicity Bias (SB)---the tendency of standard training
procedures such as Stochastic Gradient Descent (SGD) to find simple models---to justify why …

We study the problem of training deep fully connected neural networks with Rectified Linear
Unit (ReLU) activation function and cross entropy loss function for binary classification using …

We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis
perspective. We demonstrate a very universal Frequency Principle (F-Principle)---DNNs …

We study the training and generalization of deep neural networks (DNNs) in the over-
parameterized regime, where the network width (ie, number of hidden nodes per layer) is …