Yossi Arjevani

On the iteration complexity of oblivious first-order optimization algorithms

2016 · International Conference on Machine Learning

We consider a broad class of first-order optimization algorithms which are oblivious, in the sense that their step sizes are scheduled regardless of the function under consideration, except for limited side-information such as smoothness or …

On the Principle of Least Symmetry Breaking in Shallow ReLU Models

2019 · arXiv (Cornell University)

We consider the optimization problem associated with fitting two-layer ReLU networks with respect to the squared loss, where labels are assumed to be generated by a target network. Focusing first on standard Gaussian inputs, we …