Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations

Prior works for learning networks with ReLU activations assume that the bias b is zero. In order to deal with the presence of the bias terms, our proposed algorithm consists of robustly decomposing multiple higher order tensors arising from the Hermite expansion of the function f(x). Using these ideas we also establish identifiability of the network parameters under minimal assumptions.