# Parameter-Free Locally Differentially Private Stochastic Subgradient Descent

arXiv: https://arxiv.org/abs/1911.09564 · HTML: https://mlsanity.com/paper/1911.09564/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2019.

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

- [PDE-Based Optimal Strategy for Unconstrained Online Learning](https://mlsanity.com/paper/2201.07877/) (2022)
- [Optimal Comparator Adaptive Online Learning with Switching Cost](https://mlsanity.com/paper/2205.06846/) (2022)

## Abstract (arXiv)

We consider the problem of minimizing a convex risk with stochastic subgradients guaranteeing ε-locally differentially private (ε-LDP). While it has been shown that stochastic optimization is possible with ε-LDP via the standard SGD (Song et al., 2013), its convergence rate largely depends on the learning rate, which must be tuned via repeated runs. Further, tuning is detrimental to privacy loss since it significantly increases the number of gradient requests. In this work, we propose BANCO (Betting Algorithm for Noisy COins), the first ε-LDP SGD algorithm that essentially matches the convergence rate of the tuned SGD without any learning rate parameter, reducing privacy loss and saving privacy budget.