# Decentralized diffusion-based learning under non-parametric limited prior knowledge

arXiv: https://arxiv.org/abs/2305.03295 · HTML: https://mlsanity.com/paper/2305.03295/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 23 references that are in the map.
- First posted on arXiv 5 May 2023.

## Builds on (most cited first, 3 of 3)

- [Certainty Equivalent Perception-Based Control](https://mlsanity.com/paper/2008.12332/) (2020)
- [Learning linear modules in a dynamic network using regularized kernel-based methods](https://mlsanity.com/paper/2005.06266/) (2020)
- [Asynchronous adaptive networks](https://mlsanity.com/paper/1511.09180/) (2015)

## Built on by (most cited first, 2 of 2)

- [A computationally lightweight safe learning algorithm](https://mlsanity.com/paper/2309.03672/) (2023)
- [Kernel-based learning with guarantees for multi-agent applications](https://mlsanity.com/paper/2404.09708/) (2024)

## Abstract (arXiv)

We study the problem of diffusion-based network learning of a nonlinear phenomenon, m, from local agents' measurements collected in a noisy environment. For a decentralized network and information spreading merely between directly neighboring nodes, we propose a non-parametric learning algorithm, that avoids raw data exchange and requires only mild textita priori knowledge about m. Non-asymptotic estimation error bounds are derived for the proposed method. Its potential applications are illustrated through simulation experiments.