# Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions

arXiv: https://arxiv.org/abs/1606.02421 · HTML: https://mlsanity.com/paper/1606.02421/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2016.

## Built on by (most cited first, 21 of 21)

- [Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data](https://mlsanity.com/paper/2204.04452/) (2022)
- [Preserved central model for faster bidirectional compression in distributed settings](https://mlsanity.com/paper/2102.12528/) (2021)
- [Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space](https://mlsanity.com/paper/2104.00352/) (2021)
- [Distributed Learning Systems with First-order Methods](https://mlsanity.com/paper/2104.05245/) (2021)
- [Towards Demystifying Serverless Machine Learning Training](https://mlsanity.com/paper/2105.07806/) (2021)
- [D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning](https://mlsanity.com/paper/2104.07365/) (2021)
- [Opportunistic Federated Learning: An Exploration of Egocentric Collaboration for Pervasive Computing Applications](https://mlsanity.com/paper/2103.13266/) (2021)
- [Network Gradient Descent Algorithm for Decentralized Federated Learning](https://mlsanity.com/paper/2205.08364/) (2022)
- [Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means](https://mlsanity.com/paper/2505.17836/) (2025)
- [Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers](https://mlsanity.com/paper/2102.06280/) (2021)
- [iDML: Incentivized Decentralized Machine Learning](https://mlsanity.com/paper/2304.05354/) (2023)
- [Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates](https://mlsanity.com/paper/2306.06559/) (2023)
- [Optimization in Open Networks via Dual Averaging](https://mlsanity.com/paper/2105.13348/) (2021)
- [Decentralized Personalized Federated Learning](https://mlsanity.com/paper/2406.06520/) (2024)
- [Asynchronous Gossip Algorithms for Rank-Based Statistical Methods](https://mlsanity.com/paper/2509.07543/) (2025)
- [Fully Decentralized Certified Unlearning](https://mlsanity.com/paper/2512.08443/) (2025)
- [Non asymptotic bounds in asynchronous sum-weight gossip protocols](https://mlsanity.com/paper/2111.10248/) (2021)
- [DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg](https://mlsanity.com/paper/2204.02632/) (2022)
- [Addressing Data Heterogeneity in Decentralized Learning via Topological Pre-processing](https://mlsanity.com/paper/2212.08743/) (2022)
- [Optimally Improving Cooperative Learning in a Social Setting](https://mlsanity.com/paper/2405.20808/) (2024)
- [On Gossip Algorithms for Machine Learning with Pairwise Objectives](https://mlsanity.com/paper/2603.24128/) (2026)

## Abstract (arXiv)

In decentralized networks (of sensors, connected objects, etc.), there is an important need for efficient algorithms to optimize a global cost function, for instance to learn a global model from the local data collected by each computing unit. In this paper, we address the problem of decentralized minimization of pairwise functions of the data points, where these points are distributed over the nodes of a graph defining the communication topology of the network. This general problem finds applications in ranking, distance metric learning and graph inference, among others. We propose new gossip algorithms based on dual averaging which aims at solving such problems both in synchronous and asynchronous settings. The proposed framework is flexible enough to deal with constrained and regularized variants of the optimization problem. Our theoretical analysis reveals that the proposed algorithms preserve the convergence rate of centralized dual averaging up to an additive bias term. We present numerical simulations on Area Under the ROC Curve (AUC) maximization and metric learning problems which illustrate the practical interest of our approach.