论文标题
通过量化的联合兰格文蒙特卡洛（Monte Carlo）利用通道噪声进行采样和隐私
Leveraging Channel Noise for Sampling and Privacy via Quantized Federated Langevin Monte Carlo
论文作者
论文摘要
对于人工智能的工程应用，贝叶斯学习与标准频繁学习相比具有重要优势，包括量化不确定性的能力。 Langevin Monte Carlo（LMC）是一种有效的基于梯度的近似贝叶斯学习策略，旨在产生从模型参数后验分布中得出的样品。先前的工作重点是通过模拟调制在多访问无线通道上通过分布式LMC的分布式实现。相比之下，本文提出了量化的联合LMC（FLMC），该LMC（FLMC）将局部梯度的一位随机量化与通道驱动的采样相结合。通道驱动的采样利用通道噪声是为了促进蒙特卡洛采样的目的，同时还发挥了隐私机制的作用。比较无线LMC的模拟和数字实现是差异隐私（DP）要求的函数，揭示了后者在足够高的信噪比时的优势。
For engineering applications of artificial intelligence, Bayesian learning holds significant advantages over standard frequentist learning, including the capacity to quantify uncertainty. Langevin Monte Carlo (LMC) is an efficient gradient-based approximate Bayesian learning strategy that aims at producing samples drawn from the posterior distribution of the model parameters. Prior work focused on a distributed implementation of LMC over a multi-access wireless channel via analog modulation. In contrast, this paper proposes quantized federated LMC (FLMC), which integrates one-bit stochastic quantization of the local gradients with channel-driven sampling. Channel-driven sampling leverages channel noise for the purpose of contributing to Monte Carlo sampling, while also serving the role of privacy mechanism. Analog and digital implementations of wireless LMC are compared as a function of differential privacy (DP) requirements, revealing the advantages of the latter at sufficiently high signal-to-noise ratio.
