# Fast Distributed Coordinate Descent for Non-Strongly Convex Losses

arXiv: https://arxiv.org/abs/1405.5300 · HTML: https://mlsanity.com/paper/1405.5300/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2014.

## Built on by (most cited first, 4 of 4)

- [Efficient and Reliable Overlay Networks for Decentralized Federated Learning](https://mlsanity.com/paper/2112.15486/) (2021)
- [SGD with Coordinate Sampling: Theory and Practice](https://mlsanity.com/paper/2105.11818/) (2021)
- [A Privacy-Preserving and Trustable Multi-agent Learning Framework](https://mlsanity.com/paper/2106.01242/) (2021)
- [Scalable High-Dimensional Multivariate Linear Regression for Feature-Distributed Data](https://mlsanity.com/paper/2307.03410/) (2023)

## Abstract (arXiv)

We propose an efficient distributed randomized coordinate descent method for minimizing regularized non-strongly convex loss functions. The method attains the optimal O(1/k2) convergence rate, where k is the iteration counter. The core of the work is the theoretical study of stepsize parameters. We have implemented the method on Archer - the largest supercomputer in the UK - and show that the method is capable of solving a (synthetic) LASSO optimization problem with 50 billion variables.