What is it?
Cloud computing and deep learning, the recent trends in the software industry, have enabled small companies to scale their business up rapidly. However, this growth is not without a cost -- deep learning models are related to the heaviest workloads in cloud data centers.
Why is it necessary?
When the business grows, the monetary cost of deep learning in the cloud also grows fast. Deep learning practitioners should be prepared and equipped to limit the growing cost. We emphasize monetary cost instead of computational cost although often the same methods decrease both types of cost.
How does it work?
1. We performed a systematic literature review on the methods to control the cost of deep learning. We found that: 1) Optimizing inference has raised more interest than optimizing training. Widely used deep learning libraries already support inference optimization methods, such as quantization, pruning, and teacher-student. 2) The research has been centered around image inputs, and there seems to be a research gap for other types of inputs. 3) The research has been hardware-oriented, and the most typical approach to control the cost of deep learning is based on algorithm-hardware co-design. 4) Offloading some of the processing to client devices is gaining interest and can potentially reduce the monetary cost of deep learning.
2. We are now studying and testing empirically different methods based on the literature review that would work especially for non-image data.