# Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization

arXiv: https://arxiv.org/abs/2606.23210 · HTML: https://mlsanity.com/paper/2606.23210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients](https://mlsanity.com/paper/2301.11300/) (2023)
- [Concept-level Debugging of Part-Prototype Networks](https://mlsanity.com/paper/2205.15769/) (2022)
- [Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression](https://mlsanity.com/paper/2205.10369/) (2022)
- [Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML](https://mlsanity.com/paper/2305.14109/) (2023)
- [GAC-KAN: An Ultra-Lightweight GNSS Interference Classifier for GenAI-Powered Consumer Edge Devices](https://mlsanity.com/paper/2602.11186/) (2026)
- [Low-Energy On-Device Personalization for MCUs](https://mlsanity.com/paper/2403.08040/) (2024)
- [EMind: A Foundation Model for Multi-task Electromagnetic Signals Understanding](https://mlsanity.com/paper/2508.18785/) (2025)
- [GNSS Interference Classification Using Federated Reservoir Computing](https://mlsanity.com/paper/2408.13056/) (2024)
- [VAE-based Feature Disentanglement for Data Augmentation and Compression in Generalized GNSS Interference Classification](https://mlsanity.com/paper/2504.10556/) (2025)
- [Dictionary-Based Contrastive Learning for GNSS Jamming Detection](https://mlsanity.com/paper/2512.07512/) (2025)
- [PrototypeNAS: Rapid Design of Deep Neural Networks for Microcontroller Units](https://mlsanity.com/paper/2603.15106/) (2026)
- [GenAI for Energy-Efficient and Interference-Aware Compressed Sensing of GNSS Signals on a Google Edge TPU](https://mlsanity.com/paper/2605.14839/) (2026)

## Abstract (arXiv)

Embedded global navigation satellite system (GNSS) interference monitoring requires fast and memory-efficient inference to process large volumes of raw in-phase and quadrature (IQ) samples in real time. At the same time, increasingly expressive deep neural networks (DNNs) are needed for robust interference classification and characterization across diverse signal conditions. This creates a fundamental tension between predictive performance and deployability on resource-constrained hardware. In this paper, we investigate efficient network inference for GNSS interference characterization using iterative structured pruning, post-training static quantization, and hardware-aware zero-shot neural architecture search (NAS). Starting from MCUNet as a compact baseline, we analyze how model compression and automated architecture optimization affect model size, computational complexity, and memory usage while maintaining task performance. Experiments on a GNSS interference dataset, covering both classification and generalized characterization, show the benefits of combining compression and hardware-aware design for embedded deployment. Our results provide practical guidance for developing compact machine learning (ML) models for real-time GNSS interference monitoring on embedded platforms (iMXRT1062 MCU, Raspberry Pi Zero 2W, and Raspberry Pi 5).