Bayesian Inference Under Differential Privacy: Prior Selection Considerations with Application to Univariate Gaussian Data and Regression
- URL: http://arxiv.org/abs/2405.13801v1
- Date: Wed, 22 May 2024 16:27:20 GMT
- Title: Bayesian Inference Under Differential Privacy: Prior Selection Considerations with Application to Univariate Gaussian Data and Regression
- Authors: Zeki Kazan, Jerome P. Reiter,
- Abstract summary: We show that analysts can take constraints imposed by the bounds into account when specifying prior distributions.
We provide theoretical and empirical results regarding what classes of default priors produce valid inference for a differentially private release.
- Score: 0.3683202928838613
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We describe Bayesian inference for the mean and variance of bounded data protected by differential privacy and modeled as Gaussian. Using this setting, we demonstrate that analysts can and should take the constraints imposed by the bounds into account when specifying prior distributions. Additionally, we provide theoretical and empirical results regarding what classes of default priors produce valid inference for a differentially private release in settings where substantial prior information is not available. We discuss how these results can be applied to Bayesian inference for regression with differentially private data.
Related papers
- Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints [5.3595271893779906]
We study federated learning for nonparametric regression in the context of distributed samples across different servers.
Findings shed light on the tradeoff between statistical accuracy and privacy preservation.
arXiv Detail & Related papers (2024-06-10T19:34:07Z) - Approximation of Pufferfish Privacy for Gaussian Priors [6.2584995033090625]
We show that $(epsilon, delta)$-pufferfish privacy is attained if the additive Laplace noise is calibrated to the differences in mean and variance of the Gaussian distributions conditioned on every discriminative secret pair.
A typical application is the private release of the summation (or average) query.
arXiv Detail & Related papers (2024-01-22T22:43:38Z) - Optimal Unbiased Randomizers for Regression with Label Differential
Privacy [61.63619647307816]
We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP)
We demonstrate that these randomizers achieve state-of-the-art privacy-utility trade-offs on several datasets.
arXiv Detail & Related papers (2023-12-09T19:58:34Z) - Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences.
Our method is especially suitable for problems with well-specified likelihoods.
We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
arXiv Detail & Related papers (2023-11-08T00:10:21Z) - Calibrating Neural Simulation-Based Inference with Differentiable
Coverage Probability [50.44439018155837]
We propose to include a calibration term directly into the training objective of the neural model.
By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation.
It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference.
arXiv Detail & Related papers (2023-10-20T10:20:45Z) - Uncertainty-guided Source-free Domain Adaptation [77.3844160723014]
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model.
We propose quantifying the uncertainty in the source model predictions and utilizing it to guide the target adaptation.
arXiv Detail & Related papers (2022-08-16T08:03:30Z) - Differential Privacy of Dirichlet Posterior Sampling [0.0]
We study the inherent privacy of releasing a single draw from a Dirichlet posterior distribution.
With the notion of truncated concentrated differential privacy (tCDP), we are able to derive a simple privacy guarantee of the Dirichlet posterior sampling.
arXiv Detail & Related papers (2021-10-03T07:41:19Z) - Non-parametric Differentially Private Confidence Intervals for the
Median [3.205141100055992]
This paper proposes and evaluates several strategies to compute valid differentially private confidence intervals for the median.
We also illustrate that addressing both sources of uncertainty--the error from sampling and the error from protecting the output--should be preferred over simpler approaches that incorporate the uncertainty in a sequential fashion.
arXiv Detail & Related papers (2021-06-18T19:45:37Z) - Private Prediction Sets [72.75711776601973]
Machine learning systems need reliable uncertainty quantification and protection of individuals' privacy.
We present a framework that treats these two desiderata jointly.
We evaluate the method on large-scale computer vision datasets.
arXiv Detail & Related papers (2021-02-11T18:59:11Z) - Differentially Private Bayesian Inference for Generalized Linear Models [21.942149563564968]
Generalized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst's repertoire.
We introduce a generic noise-aware DP Bayesian inference method for a GLM, given a noisy sum of summary statistics.
We experimentally demonstrate that the posteriors obtained from our model, while adhering to strong privacy guarantees, are close to the non-private posteriors.
arXiv Detail & Related papers (2020-11-01T10:38:22Z) - Unlabelled Data Improves Bayesian Uncertainty Calibration under
Covariate Shift [100.52588638477862]
We develop an approximate Bayesian inference scheme based on posterior regularisation.
We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
arXiv Detail & Related papers (2020-06-26T13:50:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.