اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدSum-Rate-Distortion Function for Indirect Multiterminal Source Coding in Federated Learning
124
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
One of the main focus in federated learning (FL) is the communication efficiency since a large number of participating edge devices send their updates to the edge server at each round of the model training. Existing works reconstruct each model update from edge devices and implicitly assume that the local model updates are independent over edge devices. In FL, however, the model update is an indirect multi-terminal source coding problem, also called as the CEO problem where each edge device cannot observe directly the gradient that is to be reconstructed at the decoder, but is rather provided only with a noisy version. The existing works do not leverage the redundancy in the information transmitted by different edges. This paper studies the rate region for the indirect multiterminal source coding problem in FL. The goal is to obtain the minimum achievable rate at a particular upper bound of gradient variance. We obtain the rate region for the quadratic vector Gaussian CEO problem under unbiased estimator and derive an explicit formula of the sum-rate-distortion function in the special case where gradient are identical over edge device and dimension. Finally, we analyse communication efficiency of convex Minibatched SGD and non-convex Minibatched SGD based on the sum-rate-distortion function, respectively.
قيم البحث
اقرأ أيضاً
The rate-distortion-perception function (RDPF; Blau and Michaeli, 2019) has emerged as a useful tool for thinking about realism and distortion of reconstructions in lossy compression. Unlike the rate-distortion function, however, it is unknown whethe
r encoders and decoders exist that achieve the rate suggested by the RDPF. Building on results by Li and El Gamal (2018), we show that the RDPF can indeed be achieved using stochastic, variable-length codes. For this class of codes, we also prove that the RDPF lower-bounds the achievable rate
Federated learning (FL) as a promising edge-learning framework can effectively address the latency and privacy issues by featuring distributed learning at the devices and model aggregation in the central server. In order to enable efficient wireless
data aggregation, over-the-air computation (AirComp) has recently been proposed and attracted immediate attention. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. To combat this effect, the concept of dynamic learning rate (DLR) is proposed in this work. We begin our discussion by considering multiple-input-single-output (MISO) scenario, since the underlying optimization problem is convex and has closed-form solution. We then extend our studies to more general multiple-input-multiple-output (MIMO) case and an iterative method is derived. Extensive simulation results demonstrate the effectiveness of the proposed scheme in reducing the aggregate distortion and guaranteeing the testing accuracy using the MNIST and CIFAR10 datasets. In addition, we present the asymptotic analysis and give a near-optimal receive beamforming design solution in closed form, which is verified by numerical simulations.
The two-user interference channel is a model for multi one-to-one communications, where two transmitters wish to communicate with their corresponding receivers via a shared wireless medium. Two most common and simple coding schemes are time division
(TD) and treating interference as noise (TIN). Interestingly, it is shown that there exists an asymptotic scheme, called Han-Kobayashi scheme, that performs better than TD and TIN. However, Han-Kobayashi scheme has impractically high complexity and is designed for asymptotic settings, which leads to a gap between information theory and practice. In this paper, we focus on designing practical codes for interference channels. As it is challenging to analytically design practical codes with feasible complexity, we apply deep learning to learn codes for interference channels. We demonstrate that DeepIC, a convolutional neural network-based code with an iterative decoder, outperforms TD and TIN by a significant margin for two-user additive white Gaussian noise channels with moderate amount of interference.
The objective of this paper is to further investigate various applications of information Nonanticipative Rate Distortion Function (NRDF) by discussing two working examples, the Binary Symmetric Markov Source with parameter $p$ (BSMS($p$)) with Hammi
ng distance distortion, and the multidimensional partially observed Gaussian-Markov source. For the BSMS($p$), we give the solution to the NRDF, and we use it to compute the Rate Loss (RL) of causal codes with respect to noncausal codes. For the multidimensional Gaussian-Markov source, we give the solution to the NRDF, we show its operational meaning via joint source-channel matching over a vector of parallel Gaussian channels, and we compute the RL of causal and zero-delay codes with respect to noncausal codes.
In the context of lossy compression, Blau & Michaeli (2019) adopt a mathematical notion of perceptual quality and define the information rate-distortion-perception function, generalizing the classical rate-distortion tradeoff. We consider the notion
of universal representations in which one may fix an encoder and vary the decoder to achieve any point within a collection of distortion and perception constraints. We prove that the corresponding information-theoretic universal rate-distortion-perception function is operationally achievable in an approximate sense. Under MSE distortion, we show that the entire distortion-perception tradeoff of a Gaussian source can be achieved by a single encoder of the same rate asymptotically. We then characterize the achievable distortion-perception region for a fixed representation in the case of arbitrary distributions, identify conditions under which the aforementioned results continue to hold approximately, and study the case when the rate is not fixed in advance. This motivates the study of practical constructions that are approximately universal across the RDP tradeoff, thereby alleviating the need to design a new encoder for each objective. We provide experimental results on MNIST and SVHN suggesting that on image compression tasks, the operational tradeoffs achieved by machine learning models with a fixed encoder suffer only a small penalty when compared to their variable encoder counterparts.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
