# Infer-EDGE: Dynamic DNN Inference Optimization in 'Just-in-time' Edge-AI Implementations

arXiv: https://arxiv.org/abs/2501.18842 · HTML: https://mlsanity.com/paper/2501.18842/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2025.

## Built on by (most cited first, 4 of 4)

- [Reinforcement Learning-Driven Edge Management for Reliable Multi-view 3D Reconstruction](https://mlsanity.com/paper/2510.08839/) (2025)
- [Deep Reinforcement Learning-driven Edge Offloading for Latency-constrained XR pipelines](https://mlsanity.com/paper/2603.16823/) (2026)
- [Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference](https://mlsanity.com/paper/2603.17914/) (2026)
- [EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression](https://mlsanity.com/paper/2609.11058/) (2026)

## Abstract (arXiv)

Balancing mutually diverging performance metrics, such as end-to-end latency, accuracy, and device energy consumption, is a challenging undertaking for deep neural network (DNN) inference in Just-in-Time edge environments that are inherently resource-constrained and loosely coupled. In this paper, we design and develop the Infer-EDGE framework that seeks to strike such a balance for latency-sensitive video processing applications. First, using comprehensive benchmarking experiments, we develop intuitions about the trade-off characteristics, which are then used by the framework to develop an Advantage Actor-Critic (A2C) Reinforcement Learning (RL) approach that can choose optimal run-time DNN inference parameters aligning the performance metrics based on the application requirements. Using real-world DNNs and a hardware testbed, we evaluate the benefits of the Infer-EDGE framework in terms of device energy savings, inference accuracy improvement, and end-to-end inference latency reduction.