Faster Training of Very Deep Networks Via p-Norm Gates
This work addresses the problem of slow training in very deep networks for researchers and practitioners in machine learning, offering an incremental improvement over existing gating methods.
The paper tackles the limited analysis of gating in deep neural networks by proposing a flexible p-norm gating scheme that improves learning speed, with experiments on large datasets showing significant speed improvements without extra overhead.
A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforward models such as Residual Nets and Highway Networks. This enables learning in very deep networks with hundred layers and helps achieve record-breaking results in vision (e.g., ImageNet with Residual Nets) and NLP (e.g., machine translation with GRU). However, there is limited work in analysing the role of gating in the learning process. In this paper, we propose a flexible $p$-norm gating scheme, which allows user-controllable flow and as a consequence, improve the learning speed. This scheme subsumes other existing gating schemes, including those in GRU, Highway Networks and Residual Nets as special cases. Experiments on large sequence and vector datasets demonstrate that the proposed gating scheme helps improve the learning speed significantly without extra overhead.