paper-with-me

Papers

Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo

2015-02-26 · Yu-Xiang Wang, Stephen E. Fienberg, Alex Smola

We consider the problem of Bayesian learning on sensitive datasets and present two simple but somewhat surprising results that connect Bayesian learning to "differential privacy:, a cryptographic approach to protect individual-level privacy while permiting database-level utility. Specifically, we show that that under standard assumptions, getting one single sample from a posterior distribution is differentially private "for free". We will see that estimator is statistically consistent, near optimal and computationally tractable whenever the Bayesian model of interest is consistent, optimal and tractable. Similarly but separately, we show that a recent line of works that use stochastic gradient for Hybrid Monte Carlo (HMC) sampling also preserve differentially privacy with minor or no modifications of the algorithmic procedure at all, these observations lead to an "anytime" algorithm for Bayesian learning under privacy constraint. We demonstrate that it performs much better than the state-of-the-art differential private methods on synthetic and real datasets.

📄 PDF Abstract BibTeX arXiv:1502.07645

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning?

2021-10-11 · Guy Heller, Ethan Fetaya

Bayesian learning via Stochastic Gradient Langevin Dynamics (SGLD) has been suggested for differentially private learning. While previous research provides differential privacy bounds for SGLD at the initial steps of the…

DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton

2026-07-26 · Nour Jamoussi, Ikram Dridi, Giuseppe Serra, Marios Kountouris arxiv

Differential privacy provides formal privacy guarantees for training neural networks on sensitive data, while Bayesian deep learning offers a principled framework for uncertainty-aware prediction. Combining these two obj…

Computational Efficiency

On Connecting Stochastic Gradient MCMC and Differential Privacy

2017-12-25 · Bai Li, Changyou Chen, Hao liu, Lawrence Carin

Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and conf…

BIG-bench Machine Learning

Posterior inference unchained with EL_2O

2019-01-14 · Uros Seljak, Byeonghee Yu

Statistical inference of analytically non-tractable posteriors is a difficult problem because of marginalization of correlated variables and stochastic methods such as MCMC and VI are commonly used. We argue that stochas…

Clustering

Amplified Patch-Level Differential Privacy for Free via Random Cropping

2026-03-25 · Kaan Durmaz, Jan Schuchardt, Sebastian Schmidt, Stephan Günnemann arxiv

Random cropping is one of the most common data augmentation techniques in computer vision, yet the role of its inherent randomness in training differentially private machine learning models has thus far gone unexplored. …

Data Augmentation