1,720,990 research outputs found
Quantized Compressed Sensing for Communication-Efficient Federated Learning
No full textFederated learning (FL) is a decentralized artificial intelligence technique for training a global model on a parameter server (PS) through collaboration with wireless devices, each with its own local training data set. In this paper, we present a communication-efficient FL framework which consists of gradient compression and reconstruction strategies based on quantized compressed sensing (QCS). The key idea of the gradient compression strategy is to compress-and-quantize a local gradient vector computed at each device after sparsifying this vector in a block wise fashion. Our gradient compression strategy can make communication overhead less than one bit per gradient entry. For accurate reconstruction of the local gradient from the compressed signals at the PS, we employ a expectation-maximization generalized-approximate-message-passing algorithm. The algorithm iteratively computes an approximate minimum mean square error solution of the local gradient, while learning the unknown model parameters of the Bernoulli Gaussian-mixture prior. Using the MNIST data set, we demonstrate that the presented FL framework can achieve almost identical classification performance with the case that performs no compression, while achieving a significant reduction of communication overhead. © 2021 IEEE.1
Quantized Viterbi algorithm:Maximum likelihood sequence detection for SIMO ISI channels with low-precision ADCs
No full text1
Reinforcement-Learning-Aided ML Detector for Uplink Massive MIMO Systems with Low-Precision ADCs
No full text1
Robust Data Detection for MIMO Systems With One-Bit ADCs: A Reinforcement Learning Approach
No full textThe use of one-bit analog-to-digital converters (ADCs) at a receiver is a power-efficient solution for future wireless systems operating with a large signal bandwidth and/or a massive number of receive radio frequency chains. This solution, however, induces high channel estimation error and therefore makes it difficult to perform the optimal data detection that requires perfect knowledge of likelihood functions at the receiver. In this paper, we propose a likelihood function learning method for multiple-input multiple-output (MIMO) systems with one-bit ADCs using a reinforcement learning approach. The key idea is to exploit input-output samples obtained from data detection, to compensate for the mismatch in the likelihood function. The underlying difficulty of this idea is a label uncertainty in the samples caused by a data detection error. To resolve this problem, we define a Markov decision process (MDP) to maximize the accuracy of the likelihood function learned from the samples. We then develop a reinforcement learning algorithm that efficiently finds the optimal policy by approximating the transition function and the optimal state of the MDP. Simulation results demonstrate that the proposed method provides significant performance gains for data detection methods that suffer from the mismatch in the likelihood function.11Nsciescopu
MetaSSD: Meta-Learned Self-Supervised Detection
Get PDFDeep learning-based symbol detector gains increasing attention due to the
simple algorithm design than the traditional model-based algorithms such as
Viterbi and BCJR. The supervised learning framework is often employed to
predict the input symbols, where training symbols are used to train the model.
There are two major limitations in the supervised approaches: a) a model needs
to be retrained from scratch when new train symbols come to adapt to a new
channel status, and b) the length of the training symbols needs to be longer
than a certain threshold to make the model generalize well on unseen symbols.
To overcome these challenges, we propose a meta-learning-based self-supervised
symbol detector named MetaSSD. Our contribution is two-fold: a) meta-learning
helps the model adapt to a new channel environment based on experience with
various meta-training environments, and b) self-supervised learning helps the
model to use relatively less supervision than the previously suggested
learning-based detectors. In experiments, MetaSSD outperforms OFDM-MMSE with
noisy channel information and shows comparable results with BCJR. Further
ablation studies show the necessity of each component in our framework.Comment: Accepted by ISIT 202
On Achievable Rate of User Selection for MIMO Broadcast Channels With Limited Feedback
No full textWe consider the block diagonalization (BD) and user selection based on limited feedback in multiple antenna broadcast channels. With limited feedback, due to the imperfect channel state information at the transmitter (CSIT), BD cannot completely eliminate multiuser interference, and the throughput is correspondingly lower than that achieved with perfect CSIT. Nevertheless, the achievable multiuser diversity gain can be the same, such that limited-feedback-based BD can achieve an optimal throughput growth as the number of users increases. To show this, we first propose a channel quality indicator (CQI) for user selection. The CQI is designed to accurately estimate an achievable rate of each user and is given by an expected rate, where the expectation is solely taken over precoding matrices which cannot be known at the feedback stage. With the proper CQI, user selection can benefit from a large number of users in the system. As a result, we show that the BD can achieve an asymptotically optimal growth in throughput with the proposed CQI, based solely on a finite-rate feedback of channel information.11sciescopu
- …
