Feb 15, 2016 (modified: Feb 15, 2016)ICLR 2016 workshop submissionreaders: everyone
Abstract:Deep learning has become the state-of-art tool in many applications, but the evaluation of expressive deep models can be unfeasible on resource-constrained devices. The conditional computation approach has been proposed to tackle this problem (Bengio et al., 2013; Davis & Arel, 2013). It operates by selectively activating only parts of the network at a time. We propose to use reinforcement learning as a tool to optimize conditional computation policies. More specifically, we cast the problem of learning activation-dependent policies for dropping out blocks of units as reinforcement learning. We propose a learning scheme motivated by computation speed, capturing the idea of wanting to have parsimonious activations while maintaining prediction accuracy. We apply a policy gradient algorithm for learning policies that optimize this loss function and propose a regularization mechanism that encourages diversification of the dropout policy. We present encouraging empirical results showing that this approach improves the speed of computation without impacting the quality of the approximation.
Enter your feedback below and we'll get back to you as soon as possible.