
Random Shuffling Beats SGD Only After Many Epochs on IllConditioned Problems
Recently, there has been much interest in studying the convergence rates...
read it

The Effects of Mild Overparameterization on the Optimization Landscape of Shallow ReLU Neural Networks
We study the effects of mild overparameterization on the optimization l...
read it

How Good is SGD with Random Shuffling?
We study the performance of stochastic gradient descent (SGD) on smooth ...
read it

Depth Separations in Neural Networks: What is Actually Being Separated?
Existing depth separation results for constantdepth networks essentiall...
read it

A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance
The existence of adversarial examples in which an imperceptible change i...
read it

Spurious Local Minima are Common in TwoLayer ReLU Neural Networks
We consider the optimization problem associated with training simple ReL...
read it

DepthWidth Tradeoffs in Approximating Natural Functions with Neural Networks
We provide several new depthbased separation results for feedforward n...
read it

On the Quality of the Initial Basin in Overspecified Neural Networks
Deep learning, in the form of artificial neural networks, has achieved r...
read it
Itay Safran
verfied profile
PhD student at the Weizmann Institute of Science