# Differentially Private Stochastic Coordinate Descent

arXiv: https://arxiv.org/abs/2006.07272 · HTML: https://mlsanity.com/paper/2006.07272/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 8 of 8)

- [Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?](https://mlsanity.com/paper/2102.08166/) (2021)
- [Differentially Private Coordinate Descent for Composite Empirical Risk Minimization](https://mlsanity.com/paper/2110.11688/) (2021)
- [Improving Differentially Private SGD via Randomly Sparsified Gradients](https://mlsanity.com/paper/2112.00845/) (2021)
- [Stability and Generalization for Randomized Coordinate Descent](https://mlsanity.com/paper/2108.07414/) (2021)
- [Combining Differential Privacy and Byzantine Resilience in Distributed SGD](https://mlsanity.com/paper/2110.03991/) (2021)
- [High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent](https://mlsanity.com/paper/2207.01560/) (2022)
- [Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning](https://mlsanity.com/paper/2503.01530/) (2025)
- [Exploiting Block Coordinate Descent for Cost-Effective LLM Model Training](https://mlsanity.com/paper/2506.12037/) (2025)

## Abstract (arXiv)

In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private. Compared to the classical gradient descent algorithm where updates operate on a single model vector and controlled noise addition to this vector suffices to hide critical information about individuals, stochastic coordinate descent crucially relies on keeping auxiliary information in memory during training. This auxiliary information provides an additional privacy leak and poses the major challenge addressed in this work. Driven by the insight that under independent noise addition, the consistency of the auxiliary information holds in expectation, we present DP-SCD, the first differentially private stochastic coordinate descent algorithm. We analyze our new method theoretically and argue that decoupling and parallelizing coordinate updates is essential for its utility. On the empirical side we demonstrate competitive performance against the popular stochastic gradient descent alternative (DP-SGD) while requiring significantly less tuning.