# AOWS: Adaptive and optimal network width search with latency constraints

arXiv: https://arxiv.org/abs/2005.10481 · HTML: https://mlsanity.com/paper/2005.10481/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 17 of 17)

- [EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers](https://mlsanity.com/paper/2205.03436/) (2022)
- [Revisiting Random Channel Pruning for Neural Network Compression](https://mlsanity.com/paper/2205.05676/) (2022)
- [CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment](https://mlsanity.com/paper/2104.12642/) (2021)
- [HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning](https://mlsanity.com/paper/2106.08630/) (2021)
- [Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator](https://mlsanity.com/paper/2103.07289/) (2021)
- [Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels](https://mlsanity.com/paper/2302.05666/) (2023)
- [MAPLE: Microprocessor A Priori for Latency Estimation](https://mlsanity.com/paper/2111.15106/) (2021)
- [Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing](https://mlsanity.com/paper/2309.06047/) (2023)
- [Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping](https://mlsanity.com/paper/2404.14704/) (2024)
- [Adaptive Width Neural Networks](https://mlsanity.com/paper/2501.15889/) (2025)
- [MRF-UNets: Searching UNet with Markov Random Fields](https://mlsanity.com/paper/2207.06168/) (2022)
- [Towards Efficient Convolutional Network Models with Filter Distribution Templates](https://mlsanity.com/paper/2104.08446/) (2021)
- [Prioritized Subnet Sampling for Resource-Adaptive Supernet Training](https://mlsanity.com/paper/2109.05432/) (2021)
- [CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads](https://mlsanity.com/paper/2409.01089/) (2024)
- [Architecture Aware Latency Constrained Sparse Neural Networks](https://mlsanity.com/paper/2109.00170/) (2021)
- [Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices](https://mlsanity.com/paper/2110.08013/) (2021)
- [Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration](https://mlsanity.com/paper/2301.09312/) (2023)

## Abstract (arXiv)

Neural architecture search (NAS) approaches aim at automatically finding novel CNN architectures that fit computational constraints while maintaining a good performance on the target platform. We introduce a novel efficient one-shot NAS approach to optimally search for channel numbers, given latency constraints on a specific hardware. We first show that we can use a black-box approach to estimate a realistic latency model for a specific inference platform, without the need for low-level access to the inference computation. Then, we design a pairwise MRF to score any channel configuration and use dynamic programming to efficiently decode the best performing configuration, yielding an optimal solution for the network width search. Finally, we propose an adaptive channel configuration sampling scheme to gradually specialize the training phase to the target computational constraints. Experiments on ImageNet classification show that our approach can find networks fitting the resource constraints on different target platforms while improving accuracy over the state-of-the-art efficient networks.