Part of Advances in Neural Information Processing Systems 29 (NIPS 2016)
Behnam Neyshabur, Yuhuai Wu, Russ R. Salakhutdinov, Nati Srebro
We investigate the parameter-space geometry of recurrent neural networks (RNNs), and develop an adaptation of path-SGD optimization method, attuned to this geometry, that can learn plain RNNs with ReLU activations. On several datasets that require capturing long-term dependency structure, we show that path-SGD can significantly improve trainability of ReLU RNNs compared to RNNs trained with SGD, even with various recently suggested initialization schemes.