NIPS Proceedingsβ

Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations

Part of: Advances in Neural Information Processing Systems 29 (NIPS 2016)

[PDF] [BibTeX] [Supplemental] [Reviews]


Conference Event Type: Poster


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.