2021/12/14 by Bingzhe Wu, Wu, Bingzhe, Zhicong Liang +10
Computer Science · Engineering · Mathematics · #Markov Chains and Monte Carlo Methods #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2112.08439
arxiv created 2021/12/14 · arxiv updated 2021/12/17
Recently, generalization bounds of the non-convex empirical risk minimization paradigm using Stochastic Gradient Langevin Dynamics (SGLD) have been extensively studied. Several theoretical frameworks have been presented to study this problem from different perspectives, such as information theory and stability. In this paper, we present a unified view from privacy leakage analysis to investigate the generalization bounds of SGLD, along with a theoretical framework for re-deriving previous results in a succinct manner. Aside from theoretical findings, we conduct various numerical studies to empirically assess the information leakage issue of SGLD. Additionally, our theoretical and empirical results provide explanations for prior works that study the membership privacy of SGLD.