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

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.

Cited by in corpus (8)

• Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
• Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks
• Model Pruning Based on Quantified Similarity of Feature Maps
• MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning
• Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach
• ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
• Dual-side Sparse Tensor Core
• Architecture Aware Latency Constrained Sparse Neural Networks