Publications [#349896] of Lawrence Carin

Papers Published

1. Li, B; Chen, C; Liu, H; Carin, L, On connecting stochastic gradient MCMC and differential privacy, AISTATS 2019 - 22nd International Conference on Artificial Intelligence and Statistics (January, 2020)
   (last updated on 2024/12/31)

   Abstract:
   Concerns related to data security and confidentiality have been raised when applying machine learning to real-world applications. Differential privacy provides a principled and rigorous privacy guarantee for machine learning models. While it is common to inject noise to design a model satisfying a required differential-privacy property, it is generally hard to balance the trade-off between privacy and utility. We show that stochastic gradient Markov chain Monte Carlo (SG-MCMC) - a class of scalable Bayesian posterior sampling algorithms - satisfies strong differential privacy, when carefully chosen stepsizes are employed. We develop theory on the performance of the proposed differentially-private SG-MCMC method. We conduct experiments to support our analysis, and show that a standard SG-MCMC sampler with minor modification can reach state-of-the-art performance in terms of both privacy and utility on Bayesian learning.