# Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization

arXiv: https://arxiv.org/abs/1711.03439 · HTML: https://mlsanity.com/paper/1711.03439/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2017.

## Built on by (most cited first, 7 of 7)

- [Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums](https://mlsanity.com/paper/2102.13643/) (2021)
- [Coordinate Linear Variance Reduction for Generalized Linear Programming](https://mlsanity.com/paper/2111.01842/) (2021)
- [Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization](https://mlsanity.com/paper/2212.05088/) (2022)
- [Randomized Block-Coordinate Optimistic Gradient Algorithms for Root-Finding Problems](https://mlsanity.com/paper/2301.03113/) (2023)
- [First-Order Methods for Convex Optimization](https://mlsanity.com/paper/2101.00935/) (2021)
- [Cyclic Coordinate Dual Averaging with Extrapolation](https://mlsanity.com/paper/2102.13244/) (2021)
- [Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimization](https://mlsanity.com/paper/2303.16279/) (2023)

## Abstract (arXiv)

We propose a new randomized coordinate descent method for a convex optimization template with broad applications. Our analysis relies on a novel combination of four ideas applied to the primal-dual gap function: smoothing, acceleration, homotopy, and coordinate descent with non-uniform sampling. As a result, our method features the first convergence rate guarantees among the coordinate descent methods, that are the best-known under a variety of common structure assumptions on the template. We provide numerical evidence to support the theoretical results with a comparison to state-of-the-art algorithms.