paper-with-me

Papers

Practical Differentially Private Hyperparameter Tuning with Subsampling

2023-01-27 · NeurIPS 2023 11 · Antti Koskela, tejas kulkarni

Tuning the hyperparameters of differentially private (DP) machine learning (ML) algorithms often requires use of sensitive data and this may leak private information via hyperparameter values. Recently, Papernot and Steinke (2022) proposed a certain class of DP hyperparameter tuning algorithms, where the number of random search samples is randomized itself. Commonly, these algorithms still considerably increase the DP privacy parameter $\varepsilon$ over non-tuned DP ML model training and can be computationally heavy as evaluating each hyperparameter candidate requires a new training run. We focus on lowering both the DP bounds and the computational cost of these methods by using only a random subset of the sensitive data for the hyperparameter tuning and by extrapolating the optimal values to a larger dataset. We provide a R\'enyi differential privacy analysis for the proposed method and experimentally show that it consistently leads to better privacy-utility trade-off than the baseline method by Papernot and Steinke.

📄 PDF Abstract BibTeX arXiv:2301.11989

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Random Search Random Search replaces the exhaustive enumeration of all combinations by selecting them randomly. This can be simply applied to the discrete setting described above, but also…

Similar Papers 제목 키워드 기반

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation

2025-03-29 · Chengkun Wei, Weixian Li, Chen Gong, Wenzhi Chen

Differentially Private Stochastic Gradient Descent (DP-SGD) is a widely adopted technique for privacy-preserving deep learning. A critical challenge in DP-SGD is selecting the optimal clipping threshold C, which involves…

Deep Learningimage-classificationImage ClassificationPrivacy Preserving+1

Three Tools for Practical Differential Privacy

2018-12-07 · Koen Lennart van der Veen, Ruben Seggers, Peter Bloem, Giorgio Patrini

Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget,…

BIG-bench Machine Learning

Hyperparameter Tuning with Renyi Differential Privacy

2021-10-07 · ICLR 2022 4 · Nicolas Papernot, Thomas Steinke

For many differentially private algorithms, such as the prominent noisy stochastic gradient descent (DP-SGD), the analysis needed to bound the privacy leakage of a single training run is well understood. However, few stu…

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

2023-12-31 · NeurIPS 2023 11 · Rachel Redberg, Antti Koskela, Yu-Xiang Wang

In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versat…

Privacy Preservingregression

Efficient Hyperparameter Optimization for Differentially Private Deep Learning

2021-08-09 · Aman Priyanshu, Rakshit Naidu, FatemehSadat Mireshghallah, Mohammad Malekzadeh

Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge. Unlike the typical SGD, private datasets cannot be used many times for hyperparameter search in DPS…

Deep LearningHyperparameter Optimization