Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking

TL;DR

This paper introduces an end-to-end training framework for deep neural networks that guarantees energy consumption limits through weighted sparse projection and input masking, improving accuracy under energy constraints.

Contribution

It presents the first energy-constrained DNN training method that integrates energy estimates into the optimization process with provable efficiency.

Findings

Achieves higher accuracy at same or lower energy budgets compared to prior methods.

Provides a practical algorithm for energy-constrained DNN training.

Code is publicly available for reproducibility.

Abstract

Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time. Therefore, reducing the energy consumption has become a major design consideration in DNN training. This paper proposes the first end-to-end DNN training framework that provides quantitative energy consumption guarantees via weighted sparse projection and input masking. The key idea is to formulate the DNN training as an optimization problem in which the energy budget imposes a previously unconsidered optimization constraint. We integrate the quantitative DNN energy estimation into the DNN training process to assist the constrained optimization. We prove that an approximate algorithm can be used to efficiently solve the optimization problem. Compared to the best prior energy-saving methods, our framework trains DNNs that provide higher accuracies under same or lower energy budgets. Code is publicly available.