# HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference

arXiv: https://arxiv.org/abs/2602.06069 · HTML: https://mlsanity.com/paper/2602.06069/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 11 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)

## Built on by (most cited first, 1 of 1)

- [UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge](https://mlsanity.com/paper/2608.09291/) (2026)

## Abstract (arXiv)

The escalating demand for high-fidelity, real-time inference in distributed edge-cloud environments necessitates aggressive model optimization to counteract severe latency and energy constraints. This paper introduces the Hybrid Quantization and Pruning (HQP) framework, a novel, integrated methodology designed to achieve synergistic model acceleration while adhering to strict quality guarantees. We detail a sensitivity-aware structural pruning algorithm that employs a dynamic weight sensitivity metric, derived from a highly efficient approximation of the Fisher Information Matrix (FIM), to guide the iterative removal of redundant filters. This pruning is strictly conditional, enforcing an adherence to a maximum permissible accuracy drop (Delta ax) before the model proceeds to 8-bit post-training quantization. This rigorous coordination is critical, as it ensures the resultant sparse model structure is maximally robust to quantization error and hardware-specific kernel optimization. Exhaustive evaluation across heterogeneous NVIDIA Jetson edge platforms, utilizing resource-efficient architectures like MobileNetV3 and ResNet-18, demonstrates that the HQP framework achieves a peak performance gain of 3.12 times inference speedup and a 55 percent model size reduction, while rigorously containing the accuracy drop below the 1.5 percent constraint. A comprehensive comparative analysis against conventional single-objective compression techniques validates the HQP framework as a superior, hardware-agnostic solution for deploying ultra-low-latency AI in resource-limited edge infrastructures.