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

arXiv: https://arxiv.org/abs/1806.04321 · HTML: https://mlsanity.com/paper/1806.04321/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2018.

## Built on by (most cited first, 11 of 11)

- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [Auto-Split: A General Framework of Collaborative Edge-Cloud AI](https://mlsanity.com/paper/2108.13041/) (2021)
- [Dual-side Sparse Tensor Core](https://mlsanity.com/paper/2105.09564/) (2021)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [A Synthesis of Green Architectural Tactics for ML-Enabled Systems](https://mlsanity.com/paper/2312.09610/) (2023)
- [Model Pruning Based on Quantified Similarity of Feature Maps](https://mlsanity.com/paper/2105.06052/) (2021)
- [MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning](https://mlsanity.com/paper/2204.05274/) (2022)
- [NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes](https://mlsanity.com/paper/2306.16869/) (2023)
- [Choosing to Be Green: Advancing Green AI via Dynamic Model Selection](https://mlsanity.com/paper/2509.19996/) (2025)
- [Architecture Aware Latency Constrained Sparse Neural Networks](https://mlsanity.com/paper/2109.00170/) (2021)
- [Characterizing and Taming Resolution in Convolutional Neural Networks](https://mlsanity.com/paper/2110.14819/) (2021)

## Abstract (arXiv)

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.