# Hardware-Aware Machine Learning: Modeling and Optimization

arXiv: https://arxiv.org/abs/1809.05476 · HTML: https://mlsanity.com/paper/1809.05476/

## Key facts

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

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

- [An LLM-Tool Compiler for Fused Parallel Function Calling](https://mlsanity.com/paper/2405.17438/) (2024)
- [FLASH: Fast Neural Architecture Search with Hardware Optimization](https://mlsanity.com/paper/2108.00568/) (2021)
- [Training Machine Learning models at the Edge: A Survey](https://mlsanity.com/paper/2403.02619/) (2024)
- [LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching](https://mlsanity.com/paper/2406.06799/) (2024)
- [QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality](https://mlsanity.com/paper/2205.13045/) (2022)
- [Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey](https://mlsanity.com/paper/2601.03181/) (2026)
- [Coded-InvNet for Resilient Prediction Serving Systems](https://mlsanity.com/paper/2106.06445/) (2021)
- [Efficient Computer Vision on Edge Devices with Pipeline-Parallel Hierarchical Neural Networks](https://mlsanity.com/paper/2109.13356/) (2021)
- [QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration](https://mlsanity.com/paper/2206.15463/) (2022)
- [WeightMom: Learning Sparse Networks using Iterative Momentum-based pruning](https://mlsanity.com/paper/2208.05970/) (2022)
- [Machine Learning in Short-Reach Optical Systems: A Comprehensive Survey](https://mlsanity.com/paper/2405.09557/) (2024)

## Abstract (arXiv)

Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a plethora of design challenges related to the constraints introduced by the hardware itself. What is the latency or energy cost for an inference made by a Deep Neural Network (DNN)? Is it possible to predict this latency or energy consumption before a model is trained? If yes, how can machine learners take advantage of these models to design the hardware-optimal DNN for deployment? From lengthening battery life of mobile devices to reducing the runtime requirements of DL models executing in the cloud, the answers to these questions have drawn significant attention. One cannot optimize what isn't properly modeled. Therefore, it is important to understand the hardware efficiency of DL models during serving for making an inference, before even training the model. This key observation has motivated the use of predictive models to capture the hardware performance or energy efficiency of DL applications. Furthermore, DL practitioners are challenged with the task of designing the DNN model, i.e., of tuning the hyper-parameters of the DNN architecture, while optimizing for both accuracy of the DL model and its hardware efficiency. Therefore, state-of-the-art methodologies have proposed hardware-aware hyper-parameter optimization techniques. In this paper, we provide a comprehensive assessment of state-of-the-art work and selected results on the hardware-aware modeling and optimization for DL applications. We also highlight several open questions that are poised to give rise to novel hardware-aware designs in the next few years, as DL applications continue to significantly impact associated hardware systems and platforms.