Private Generative Bootstrap via Blocking

• URL: http://arxiv.org/abs/2608.02480v1
• Date: Mon, 03 Aug 2026 16:47:14 GMT
• Title: Private Generative Bootstrap via Blocking
• Abstract summary: We propose a new private instantiation of the Bayesian bootstrap using a blocking strategy.<n>Rather than assigning idiosyncratic random weights to each individual, we randomly group individuals and assign a single weight to each group.<n>We show a single fit of PGBB can support a family of loss-based decision rules simultaneously without additional privacy cost.
• Score: 1.1816942730023885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With AI systems gaining more access to individuals' information, it is important to protect privacy when reporting statistical answers. Equally important is to privatize the reporting of uncertainty in such answers. To this end, we adopt a Bayesian likelihood-free framework and make simulation from the posterior private. In particular, we propose a new private instantiation of the Bayesian bootstrap using a blocking strategy. Rather than assigning idiosyncratic random weights to each individual, we randomly group individuals and assign a single weight to each group. By concealing individuals' contributions within a group, we fortify differential privacy gates. We harness amortized inference that decouples private learning from posterior sampling. A push-forward map from observation weights to posterior samples is learned privately by adding calibrated noise during training. Subsequent posterior draws require no additional privacy and computation budget. We call the resulting method the Private Generative Bayesian Bootstrap (PGBB). We establish a differential privacy guarantee, analyze convergence to the non-private blocked-bootstrap target, and quantify the discrepancy between the ordinary and blocked Bayesian-bootstrap posteriors. In addition, we derive data-free tuning of the block Dirichlet concentration parameter that restores posterior dispersion asymptotically. We also show a single fit of PGBB can support a family of loss-based decision rules simultaneously without additional privacy cost. In simulations and in applications to U.S. Census returns to schooling and U.S. natality birthweight quantiles, PGBB gives competitive private uncertainty quantification and improves over private Bayesian alternatives that require a specified data-generating model in common settings.

Related papers

• Privacy Without Regret: Differentially Private Inference-Time Alignment [8.568849346613602]
  We show that a single intervention-adding noise to reward scores before selection-resolves both.<n>PrivBoN establishes that Gumbel noise at an appropriate scale simultaneously provides $$-differential privacy.<n>PrivITP achieves ex-post $(,)$-DP with a privacy cost independent of the number of responses.
  arXiv  Detail & Related papers  (2026-08-26T18:56:27Z)
• Differential Privacy of Gaussian Process Posterior Sampling [0.0]
  We study the privacy of releasing posterior sample paths from a Gaussian process (GP)<n>Unlike standard differential-privacy (DP) mechanisms that add external noise, posterior sampling is random by construction.<n>We show that this intrinsic randomness yields DP guarantees by deriving explicit Rényi-DP bounds for GP posterior sample-path release.
  arXiv  Detail & Related papers  (2026-06-16T14:43:16Z)
• Gaussian Differential Private Bootstrap by Subsampling [1.0742675209112622]
  We propose a private empirical $m$ out of $n$ bootstrap and validate its consistency and privacy guarantees under Differential Privacy.<n>Compared to the the private $n$ out of $n$ bootstrap, our approach has several advantages. First, it comes with less computational costs, in particular for massive data.
  arXiv  Detail & Related papers  (2025-05-02T11:40:50Z)
• Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression [66.93988594607842]
  Under privacy constraints, the complexity of private linear regression is emphnot captured by the usual covariance matrix.<n>We introduce an Information-Weighted Regression method that attains the optimal rates.<n> Notably, our results demonstrate that joint privacy comes at almost no additional cost.
  arXiv  Detail & Related papers  (2025-02-18T18:35:24Z)
• Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent [1.0742675209112622]
  Gradient Descent (SGD) is a widely used tool in machine learning. Uncertainty quantification (UQ) for SGD by bootstrap has been addressed by several authors. We propose a novel block bootstrap for SGD under local differential privacy.
  arXiv  Detail & Related papers  (2024-05-21T07:47:21Z)
• Privacy Amplification for the Gaussian Mechanism via Bounded Support [64.86780616066575]
  Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. We propose simple modifications of the Gaussian mechanism with bounded support, showing that they amplify privacy guarantees under data-dependent accounting.
  arXiv  Detail & Related papers  (2024-03-07T21:22:07Z)
• Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks [72.51255282371805]
  We prove a privacy bound for the KL divergence between model distributions on worst-case neighboring datasets. We find that this KL privacy bound is largely determined by the expected squared gradient norm relative to model parameters during training.
  arXiv  Detail & Related papers  (2023-10-31T16:13:22Z)
• Differentially Private Computation of Basic Reproduction Numbers in Networked Epidemic Models [3.1966459264817875]
  We develop a framework to compute and release the reproduction number of a networked epidemic model in a differentially private way. We show that, under real-world conditions, we can compute $R_0$ in a differentially private way while incurring errors as low as $7.6%$ on average.
  arXiv  Detail & Related papers  (2023-09-29T14:38:02Z)
• Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent [69.14164921515949]
  We characterize privacy guarantees for individual examples when releasing models trained by DP-SGD. We find that most examples enjoy stronger privacy guarantees than the worst-case bound. This implies groups that are underserved in terms of model utility simultaneously experience weaker privacy guarantees.
  arXiv  Detail & Related papers  (2022-06-06T13:49:37Z)
• Nonparametric extensions of randomized response for private confidence sets [51.75485869914048]
  This work derives methods for performing nonparametric, nonasymptotic statistical inference for population means under the constraint of local differential privacy (LDP) We present confidence intervals (CI) and time-uniform confidence sequences (CS) for $mustar$ when only given access to the privatized data.
  arXiv  Detail & Related papers  (2022-02-17T16:04:49Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)
• Privacy Amplification via Random Check-Ins [38.72327434015975]
  Differentially Private Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. In this paper, we focus on conducting iterative methods like DP-SGD in the setting of federated learning (FL) wherein the data is distributed among many devices (clients) Our main contribution is the emphrandom check-in distributed protocol, which crucially relies only on randomized participation decisions made locally and independently by each client.
  arXiv  Detail & Related papers  (2020-07-13T18:14:09Z)

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.