# Private Domain Adaptation from a Public Source

arXiv: https://arxiv.org/abs/2208.06135 · HTML: https://mlsanity.com/paper/2208.06135/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 12 Aug 2022.

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

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Private Stochastic Convex Optimization: Optimal Rates in ℓ1 Geometry](https://mlsanity.com/paper/2103.01516/) (2021)
- [Private Learning and Sanitization: Pure vs. Approximate Differential Privacy](https://mlsanity.com/paper/1407.2674/) (2014)
- [Non-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Time](https://mlsanity.com/paper/2103.01278/) (2021)
- [Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings](https://mlsanity.com/paper/2107.05585/) (2021)
- [Limits of Private Learning with Access to Public Data](https://mlsanity.com/paper/1910.11519/) (2019)
- [Private Query Release Assisted by Public Data](https://mlsanity.com/paper/2004.10941/) (2020)
- [Privately Answering Classification Queries in the Agnostic PAC Model](https://mlsanity.com/paper/1907.13553/) (2019)

## Built on by (most cited first, 3 of 3)

- [Oracle-Efficient Differentially Private Learning with Public Data](https://mlsanity.com/paper/2402.09483/) (2024)
- [Learning-Augmented Private Algorithms for Multiple Quantile Release](https://mlsanity.com/paper/2210.11222/) (2022)
- [Differentially Private Domain Adaptation with Theoretical Guarantees](https://mlsanity.com/paper/2306.08838/) (2023)

## Abstract (arXiv)

A key problem in a variety of applications is that of domain adaptation from a public source domain, for which a relatively large amount of labeled data with no privacy constraints is at one's disposal, to a private target domain, for which a private sample is available with very few or no labeled data. In regression problems with no privacy constraints on the source or target data, a discrepancy minimization algorithm based on several theoretical guarantees was shown to outperform a number of other adaptation algorithm baselines. Building on that approach, we design differentially private discrepancy-based algorithms for adaptation from a source domain with public labeled data to a target domain with unlabeled private data. The design and analysis of our private algorithms critically hinge upon several key properties we prove for a smooth approximation of the weighted discrepancy, such as its smoothness with respect to the ℓ1-norm and the sensitivity of its gradient. Our solutions are based on private variants of Frank-Wolfe and Mirror-Descent algorithms. We show that our adaptation algorithms benefit from strong generalization and privacy guarantees and report the results of experiments demonstrating their effectiveness.