Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better

TL;DR

This survey comprehensively reviews techniques and hardware considerations for making deep learning models smaller, faster, and more resource-efficient, providing practical guidance and insights for researchers and practitioners.

Contribution

It is the first extensive survey covering model efficiency techniques, infrastructure, and hardware, with an experimental guide and code for optimization.

Findings

Identifies five core areas of model efficiency.

Provides a practical guide with code for optimization.

Highlights the importance of hardware in model efficiency.

Abstract

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. However, with the progressive improvements in deep learning models, their number of parameters, latency, resources required to train, etc. have all have increased significantly. Consequently, it has become important to pay attention to these footprint metrics of a model as well, not just its quality. We present and motivate the problem of efficiency in deep learning, followed by a thorough survey of the five core areas of model efficiency (spanning modeling techniques, infrastructure, and hardware) and the seminal work there. We also present an experiment-based guide along with code, for practitioners to optimize their model training and deployment. We believe this is the first comprehensive survey in the efficient deep learning space that covers the landscape of model efficiency from modeling techniques to hardware support. Our hope is that this survey would provide the reader with the mental model and the necessary understanding of the field to apply generic efficiency techniques to immediately get significant improvements, and also equip them with ideas for further research and experimentation to achieve additional gains.