Conditional Computation in Neural Networks for faster models

TL;DR

This paper introduces a reinforcement learning-based method to optimize conditional computation policies in neural networks, enabling faster inference while maintaining accuracy.

Contribution

It proposes a novel reinforcement learning framework to learn activation-dependent dropout policies that improve computational efficiency in neural networks.

Findings

Faster neural network inference without loss of accuracy.

Reinforcement learning effectively optimizes activation policies.

Regularization encourages diverse and efficient activation patterns.

Abstract

Deep learning has become the state-of-art tool in many applications, but the evaluation and training of deep models can be time-consuming and computationally expensive. 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. In this paper, we 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 a reinforcement learning problem. 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.