Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.04290 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911138463088640 |
|---|---|
| author | Yang, Yaohong Rehn, Aki Katt, Sammie Honkela, Antti Kaski, Samuel |
| author_facet | Yang, Yaohong Rehn, Aki Katt, Sammie Honkela, Antti Kaski, Samuel |
| contents | Differential privacy (DP) is the standard for privacy-preserving analysis, and introduces a fundamental trade-off between privacy guarantees and model performance. Selecting the optimal balance is a critical challenge that can be framed as a multi-objective optimization (MOO) problem where one first discovers the set of optimal trade-offs (the Pareto front) and then learns a decision-maker's preference over them. While a rich body of work on interactive MOO exists, the standard approach -- modeling the objective functions with generic surrogates and learning preferences from simple pairwise feedback -- is inefficient for DP because it fails to leverage the problem's unique structure: a point on the Pareto front can be generated directly by maximizing accuracy for a fixed privacy level. Motivated by this property, we first derive the shape of the trade-off theoretically, which allows us to model the Pareto front directly and efficiently. To address inefficiency in preference learning, we replace pairwise comparisons with a more informative interaction. In particular, we present the user with hypothetical trade-off curves and ask them to pick their preferred trade-off. Our experiments on differentially private logistic regression and deep transfer learning across six real-world datasets show that our method converges to the optimal privacy-accuracy trade-off with significantly less computational cost and user interaction than baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04290 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy Yang, Yaohong Rehn, Aki Katt, Sammie Honkela, Antti Kaski, Samuel Machine Learning Differential privacy (DP) is the standard for privacy-preserving analysis, and introduces a fundamental trade-off between privacy guarantees and model performance. Selecting the optimal balance is a critical challenge that can be framed as a multi-objective optimization (MOO) problem where one first discovers the set of optimal trade-offs (the Pareto front) and then learns a decision-maker's preference over them. While a rich body of work on interactive MOO exists, the standard approach -- modeling the objective functions with generic surrogates and learning preferences from simple pairwise feedback -- is inefficient for DP because it fails to leverage the problem's unique structure: a point on the Pareto front can be generated directly by maximizing accuracy for a fixed privacy level. Motivated by this property, we first derive the shape of the trade-off theoretically, which allows us to model the Pareto front directly and efficiently. To address inefficiency in preference learning, we replace pairwise comparisons with a more informative interaction. In particular, we present the user with hypothetical trade-off curves and ask them to pick their preferred trade-off. Our experiments on differentially private logistic regression and deep transfer learning across six real-world datasets show that our method converges to the optimal privacy-accuracy trade-off with significantly less computational cost and user interaction than baselines. |
| title | An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.04290 |