Generalization Bounds for Stochastic Gradient Langevin Dynamics: A Unified View via Information Leakage Analysis
Wu, Bingzhe, Liang, Zhicong, Bian, Yatao, Chen, ChaoChao, Huang, Junzhou, Yao, Yuan
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Dec-14-2021
- Country:
- North America
- United States
- Oregon > Multnomah County
- Portland (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- California
- Los Angeles County > Long Beach (0.04)
- Santa Clara County > San Jose (0.04)
- Oregon > Multnomah County
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.14)
- United States
- Europe
- Asia
- Middle East > Jordan (0.04)
- China > Beijing
- Beijing (0.04)
- North America
- Genre:
- Research Report (0.64)
- Industry:
- Information Technology > Security & Privacy (1.00)