# Distributed Gradient Clustering: Convergence and the Effect of Initialization

arXiv: https://arxiv.org/abs/2603.20507 · HTML: https://mlsanity.com/paper/2603.20507/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 10 of 10)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [The Hardness of Approximation of Euclidean k-means](https://mlsanity.com/paper/1502.03316/) (2015)
- [Distributed k-Means and k-Median Clustering on General Topologies](https://mlsanity.com/paper/1306.0604/) (2013)
- [Personalized Federated Learning via Convex Clustering](https://mlsanity.com/paper/2202.00718/) (2022)
- [Networked Signal and Information Processing](https://mlsanity.com/paper/2210.13767/) (2022)
- [Gradient Based Clustering](https://mlsanity.com/paper/2202.00720/) (2022)
- [Distributed k-means algorithm](https://mlsanity.com/paper/1312.4176/) (2013)
- [Clustering with Distributed Data](https://mlsanity.com/paper/1901.00214/) (2019)
- [A One-shot Framework for Distributed Clustered Learning in Heterogeneous Environments](https://mlsanity.com/paper/2209.10866/) (2022)

## Abstract (arXiv)

We study the effects of center initialization on the performance of a family of distributed gradient-based clustering algorithms introduced in [1], that work over connected networks of users. In the considered scenario, each user contains a local dataset and communicates only with its immediate neighbours, with the aim of finding a global clustering of the joint data. We perform extensive numerical experiments, evaluating the effects of center initialization on the performance of our family of methods, demonstrating that our methods are more resilient to the effects of initialization, compared to centralized gradient clustering [2]. Next, inspired by the K-means++ initialization [3], we propose a novel distributed center initialization scheme, which is shown to improve the performance of our methods, compared to the baseline random initialization.