# DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime

arXiv: https://arxiv.org/abs/2305.10294 · HTML: https://mlsanity.com/paper/2305.10294/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 58 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 30 of 32)

- [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)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Tighter Theory for Local SGD on Identical and Heterogeneous Data](https://mlsanity.com/paper/1909.04746/) (2019)
- [FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data](https://mlsanity.com/paper/2005.11418/) (2020)
- [Generalized Federated Learning via Sharpness Aware Minimization](https://mlsanity.com/paper/2206.02618/) (2022)
- [ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!](https://mlsanity.com/paper/2202.09357/) (2022)
- [Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients](https://mlsanity.com/paper/2102.07053/) (2021)
- [FedSplit: An algorithmic framework for fast federated optimization](https://mlsanity.com/paper/2005.05238/) (2020)
- [Local SGD: Unified Theory and New Efficient Methods](https://mlsanity.com/paper/2011.02828/) (2020)
- [FedCM: Federated Learning with Client-level Momentum](https://mlsanity.com/paper/2106.10874/) (2021)
- [Communication Complexity of Distributed Convex Learning and Optimization](https://mlsanity.com/paper/1506.01900/) (2015)
- [How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD](https://mlsanity.com/paper/1801.02982/) (2018)
- [Federated Composite Optimization](https://mlsanity.com/paper/2011.08474/) (2020)
- [Incremental Gradient, Subgradient, and Proximal Methods for Convex Optimization: A Survey](https://mlsanity.com/paper/1507.01030/) (2015)
- [An optimal randomized incremental gradient method](https://mlsanity.com/paper/1507.02000/) (2015)
- [Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning](https://mlsanity.com/paper/2207.04338/) (2022)
- [The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication](https://mlsanity.com/paper/2102.01583/) (2021)
- [FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization](https://mlsanity.com/paper/2103.03452/) (2021)
- [RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates](https://mlsanity.com/paper/2207.12891/) (2022)
- [Can 5th Generation Local Training Methods Support Client Sampling? Yes!](https://mlsanity.com/paper/2212.14370/) (2022)
- [On the Complexity Analysis of Randomized Block-Coordinate Descent Methods](https://mlsanity.com/paper/1305.4723/) (2013)
- [Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox](https://mlsanity.com/paper/2207.03957/) (2022)
- [Optimizing the Efficiency of First-Order Methods for Decreasing the Gradient of Smooth Convex Functions](https://mlsanity.com/paper/1803.06600/) (2018)
- [Backtracking strategies for accelerated descent methods with smooth composite objectives](https://mlsanity.com/paper/1709.09004/) (2017)
- [Adaptive Restart of the Optimized Gradient Method for Convex Optimization](https://mlsanity.com/paper/1703.04641/) (2017)
- [Principled Analyses and Design of First-Order Methods with Inexact Proximal Operators](https://mlsanity.com/paper/2006.06041/) (2020)
- [Additive Schwarz Methods for Convex Optimization as Gradient Methods](https://mlsanity.com/paper/1912.03617/) (2019)

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

- [Fisher-Informed Parameterwise Aggregation for Federated Learning with Heterogeneous Data](https://mlsanity.com/paper/2601.13608/) (2026)
- [Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps](https://mlsanity.com/paper/2407.02689/) (2024)

## Abstract (arXiv)

We propose a new training algorithm, named DualFL (Dualized Federated Learning), for solving distributed optimization problems in federated learning. DualFL achieves communication acceleration for very general convex cost functions, thereby providing a solution to an open theoretical problem in federated learning concerning cost functions that may not be smooth nor strongly convex. We provide a detailed analysis for the local iteration complexity of DualFL to ensure the overall computational efficiency of DualFL. Furthermore, we introduce a completely new approach for the convergence analysis of federated learning based on a dual formulation. This new technique enables concise and elegant analysis, which contrasts the complex calculations used in existing literature on convergence of federated learning algorithms.