# Performances of Symmetric Loss for Private Data from Exponential Mechanism

arXiv: https://arxiv.org/abs/2210.04132 · HTML: https://mlsanity.com/paper/2210.04132/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 9 of 9)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Conditional Learning of Fair Representations](https://mlsanity.com/paper/1910.07162/) (2019)
- [Making Risk Minimization Tolerant to Label Noise](https://mlsanity.com/paper/1403.3610/) (2014)
- [On Symmetric Losses for Learning from Corrupted Labels](https://mlsanity.com/paper/1901.09314/) (2019)
- [Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curve](https://mlsanity.com/paper/1605.04337/) (2016)
- [Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA](https://mlsanity.com/paper/1901.10864/) (2019)
- [Differentially-Private Two-Party Egocentric Betweenness Centrality](https://mlsanity.com/paper/1901.05562/) (2019)

## Abstract (arXiv)

This study explores the robustness of learning by symmetric loss on private data. Specifically, we leverage exponential mechanism (EM) on private labels. First, we theoretically re-discussed properties of EM when it is used for private learning with symmetric loss. Then, we propose numerical guidance of privacy budgets corresponding to different data scales and utility guarantees. Further, we conducted experiments on the CIFAR-10 dataset to present the traits of symmetric loss. Since EM is a more generic differential privacy (DP) technique, it being robust has the potential for it to be generalized, and to make other DP techniques more robust.