# Pre-Deployment Complexity Estimation for Federated Perception Systems

arXiv: https://arxiv.org/abs/2603.28282 · HTML: https://mlsanity.com/paper/2603.28282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [EMNIST: an extension of MNIST to handwritten letters](https://mlsanity.com/paper/1702.05373/) (2017)
- [Scikit-dimension: a Python package for intrinsic dimension estimation](https://mlsanity.com/paper/2109.02596/) (2021)
- [An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition](https://mlsanity.com/paper/2008.10400/) (2020)
- [Fine-Tuning DARTS for Image Classification](https://mlsanity.com/paper/2006.09042/) (2020)
- [Understanding the (un)interpretability of natural image distributions using generative models](https://mlsanity.com/paper/1901.01499/) (2019)
- [Measuring the Complexity of Domains Used to Evaluate AI Systems](https://mlsanity.com/paper/2010.01985/) (2020)

## Abstract (arXiv)

Edge AI systems increasingly rely on federated learning to train perception models in distributed, privacy-preserving, and resource-constrained environments. Before training, however, practitioners often lack practical tools for estimating task difficulty in terms of expected accuracy and communication effort. We present a classifier-agnostic, pre-deployment framework that combines intrinsic data properties such as dimensionality, sparsity, and heterogeneity, with client-distribution composition to estimate learning complexity in federated perception systems. Using federated learning as a representative distributed training setting, we examine how learning difficulty varies across different federated configurations. Experiments on three MNIST variants show strong negative correlations between the combined complexity metric and maximum and average federated accuracy, while the intrinsic and distributed components exhibit consistent relationships with communication effort. These findings suggest that complexity estimation can serve as a practical diagnostic tool for resource planning, dataset assessment, and feasibility evaluation in edge-deployed perception systems.