اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدWireless Federated Langevin Monte Carlo: Repurposing Channel Noise for Bayesian Sampling and Privacy
101
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Most works on federated learning (FL) focus on the most common frequentist formulation of learning whereby the goal is minimizing the global empirical loss. Frequentist learning, however, is known to be problematic in the regime of limited data as it fails to quantify epistemic uncertainty in prediction. Bayesian learning provides a principled solution to this problem by shifting the optimization domain to the space of distribution in the model parameters. This paper studies for the first time Bayesian FL in wireless systems by proposing and analyzing a gradient-based Markov Chain Monte Carlo (MCMC) method -- Wireless Federated Langevin Monte Carlo (WFLMC). The key idea of this work is to repurpose channel noise for the double role of seed randomness for MCMC sampling and of privacy-preserving mechanism. To this end, based on the analysis of the Wasserstein distance between sample distribution and global posterior distribution under privacy and power constraints, we introduce a power allocation strategy as the solution of a convex program. The analysis identifies distinct operating regimes in which the performance of the system is power-limited, privacy-limited, or limited by the requirement of MCMC sampling. Both analytical and simulation results demonstrate that, if the channel noise is properly accounted for under suitable conditions, it can be fully repurposed for both MCMC sampling and privacy preservation, obtaining the same performance as in an ideal communication setting that is not subject to privacy constraints.
قيم البحث
اقرأ أيضاً
Conventional frequentist learning, as assumed by existing federated learning protocols, is limited in its ability to quantify uncertainty, incorporate prior knowledge, guide active learning, and enable continual learning. Bayesian learning provides a
principled approach to address all these limitations, at the cost of an increase in computational complexity. This paper studies distributed Bayesian learning in a wireless data center setting encompassing a central server and multiple distributed workers. Prior work on wireless distributed learning has focused exclusively on frequentist learning, and has introduced the idea of leveraging uncoded transmission to enable over-the-air computing. Unlike frequentist learning, Bayesian learning aims at evaluating approximations or samples from a global posterior distribution in the model parameter space. This work investigates for the first time the design of distributed one-shot, or embarrassingly parallel, Bayesian learning protocols in wireless data centers via consensus Monte Carlo (CMC). Uncoded transmission is introduced not only as a way to implement over-the-air computing, but also as a mechanism to deploy channel-driven MC sampling: Rather than treating channel noise as a nuisance to be mitigated, channel-driven sampling utilizes channel noise as an integral part of the MC sampling process. A simple wireless CMC scheme is first proposed that is asymptotically optimal under Gaussian local posteriors. Then, for arbitrary local posteriors, a variational optimization strategy is introduced. Simulation results demonstrate that, if properly accounted for, channel noise can indeed contribute to MC sampling and does not necessarily decrease the accuracy level.
Federated Learning (FL) refers to distributed protocols that avoid direct raw data exchange among the participating devices while training for a common learning task. This way, FL can potentially reduce the information on the local data sets that is
leaked via communications. In order to provide formal privacy guarantees, however, it is generally necessary to put in place additional masking mechanisms. When FL is implemented in wireless systems via uncoded transmission, the channel noise can directly act as a privacy-inducing mechanism. This paper demonstrates that, as long as the privacy constraint level, measured via differential privacy (DP), is below a threshold that decreases with the signal-to-noise ratio (SNR), uncoded transmission achieves privacy for free, i.e., without affecting the learning performance. More generally, this work studies adaptive power allocation (PA) for decentralized gradient descent in wireless FL with the aim of minimizing the learning optimality gap under privacy and power constraints. Both orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) transmission with over-the-air-computing are studied, and solutions are obtained in closed form for an offline optimization setting. Furthermore, heuristic online methods are proposed that leverage iterative one-step-ahead optimization. The importance of dynamic PA and the potential benefits of NOMA versus OMA are demonstrated through extensive simulations.
In a wireless network that conveys status updates from sources (i.e., sensors) to destinations, one of the key issues studied by existing literature is how to design an optimal source sampling strategy on account of the communication constraints whic
h are often modeled as queues. In this paper, an alternative perspective is presented -- a novel status-aware communication scheme, namely emph{parallel communications}, is proposed which allows sensors to be communication-agnostic. Specifically, the proposed scheme can determine, based on an online prediction functionality, whether a status packet is worth transmitting considering both the network condition and status prediction, such that sensors can generate status packets without communication constraints. We evaluate the proposed scheme on a Software-Defined-Radio (SDR) test platform, which is integrated with a collaborative autonomous driving simulator, i.e., Simulation-of-Urban-Mobility (SUMO), to produce realistic vehicle control models and road conditions. The results show that with online status predictions, the channel occupancy is significantly reduced, while guaranteeing low status recovery error. Then the framework is applied to two scenarios: a multi-density platooning scenario, and a flight formation control scenario. Simulation results show that the scheme achieves better performance on the network level, in terms of keeping the minimum safe distance in both vehicle platooning and flight control.
The Hamiltonian Monte Carlo (HMC) sampling algorithm exploits Hamiltonian dynamics to construct efficient Markov Chain Monte Carlo (MCMC), which has become increasingly popular in machine learning and statistics. Since HMC uses the gradient informati
on of the target distribution, it can explore the state space much more efficiently than the random-walk proposals. However, probabilistic inference involving multi-modal distributions is very difficult for standard HMC method, especially when the modes are far away from each other. Sampling algorithms are then often incapable of traveling across the places of low probability. In this paper, we propose a novel MCMC algorithm which aims to sample from multi-modal distributions effectively. The method improves Hamiltonian dynamics to reduce the autocorrelation of the samples and uses a variational distribution to explore the phase space and find new modes. A formal proof is provided which shows that the proposed method can converge to target distributions. Both synthetic and real datasets are used to evaluate its properties and performance. The experimental results verify the theory and show superior performance in multi-modal sampling.
Hamiltonian Monte Carlo (HMC) is an efficient Bayesian sampling method that can make distant proposals in the parameter space by simulating a Hamiltonian dynamical system. Despite its popularity in machine learning and data science, HMC is inefficien
t to sample from spiky and multimodal distributions. Motivated by the energy-time uncertainty relation from quantum mechanics, we propose a Quantum-Inspired Hamiltonian Monte Carlo algorithm (QHMC). This algorithm allows a particle to have a random mass matrix with a probability distribution rather than a fixed mass. We prove the convergence property of QHMC and further show why such a random mass can improve the performance when we sample a broad class of distributions. In order to handle the big training data sets in large-scale machine learning, we develop a stochastic gradient version of QHMC using Nos{e}-Hoover thermostat called QSGNHT, and we also provide theoretical justifications about its steady-state distributions. Finally in the experiments, we demonstrate the effectiveness of QHMC and QSGNHT on synthetic examples, bridge regression, image denoising and neural network pruning. The proposed QHMC and QSGNHT can indeed achieve much more stable and accurate sampling results on the test cases.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
