I'm looking for some good references that give convergence results of training neural networks. I'm decently familiar with works that analyze the convergence of SGD, and, in particular, I really like this paper Optimization Methods for Large-Scale Machine Learning. I'm looking for works that talk about the convergence of SGD (or possibly a different gradient-based algorithm) specifically for neural networks.

An example of the type of paper I'm looking for is Convergence Analysis of Two-layer Neural Networks with ReLU Activation.



You must log in to answer this question.