Online Meta-Learning For Hybrid Model-Based Deep Receivers

Recent years have witnessed growing interest in the application of deep neural networks (DNNs) for receiver design, which can potentially be applied in complex environments without relying on knowledge of the channel model. However, the dynamic nature of communication channels often leads to rapid distribution shifts, which may require periodically retraining. This paper formulates a data-efficient two-stage training method that facilitates rapid online adaptation. Our training mechanism uses a predictive meta-learning scheme to train rapidly from data corresponding to both current and past channel realizations. Our method is applicable to any deep neural network (DNN)-based receiver, and does not require transmission of new pilot data for training. To illustrate the proposed approach, we study DNN-aided receivers that utilize an interpretable model-based architecture, and introduce a modular training strategy based on predictive meta-learning. We demonstrate our techniques in simulations on a synthetic linear channel, a synthetic non-linear channel, and a COST 2100 channel. Our results demonstrate that the proposed online training scheme allows receivers to outperform previous techniques based on self-supervision and joint-learning by a margin of up to 2.5 dB in coded bit error rate in rapidly-varying scenarios.

Predicting Multi-Antenna Frequency-Selective Channels via Meta-Learned Linear Filters based on Long-Short Term Channel Decomposition

An efficient data-driven prediction strategy for multi-antenna frequency-selective channels must operate based on a small number of pilot symbols. This paper proposes novel channel prediction algorithms that address this goal by integrating transfer and meta-learning with a reduced-rank parametrization of the channel. The proposed methods optimize linear predictors by utilizing data from previous frames, which are generally characterized by distinct propagation characteristics, in order to enable fast training on the time slots of the current frame. The proposed predictors rely on a novel long-short-term decomposition (LSTD) of the linear prediction model that leverages the disaggregation of the channel into long-term space-time signatures and fading amplitudes. We first develop predictors for single-antenna frequency-flat channels based on transfer/meta-learned quadratic regularization. Then, we introduce transfer and meta-learning algorithms for LSTD-based prediction models that build on equilibrium propagation (EP) and alternating least squares (ALS). Numerical results under the 3GPP 5G standard channel model demonstrate the impact of transfer and meta-learning on reducing the number of pilots for channel prediction, as well as the merits of the proposed LSTD parametrization.

Robust Design of Rate-Splitting Multiple Access With Imperfect CSI for Cell-Free MIMO Systems

Rate-Splitting Multiple Access (RSMA) for multi-user downlink operates by splitting the message for each user equipment (UE) into a private message and a set of common messages, which are simultaneously transmitted by means of superposition coding. The RSMA scheme can enhance throughput and connectivity as compared to conventional multiple access techniques by optimizing the rate-splitting ratios along with the corresponding downlink beamforming vectors. This work examines the impact of erroneous channel state information (CSI) on the performance of RSMA in cell-free multiple-input multiple-output (MIMO) systems. An efficient robust optimization algorithm is proposed by using closed-form lower bound expressions on the expected data rates. Extensive numerical results show the importance of robust design in the presence of CSI errors and how the performance gain of RSMA over conventional schemes is affected by CSI imperfection.

Robust PAC$^m$: Training Ensemble Models Under Model Misspecification and Outliers

Standard Bayesian learning is known to have suboptimal generalization capabilities under model misspecification and in the presence of outliers. PAC-Bayes theory demonstrates that the free energy criterion minimized by Bayesian learning is a bound on the generalization error for Gibbs predictors (i.e., for single models drawn at random from the posterior) under the assumption of sampling distributions uncontaminated by outliers. This viewpoint provides a justification for the limitations of Bayesian learning when the model is misspecified, requiring ensembling, and when data is affected by outliers. In recent work, PAC-Bayes bounds - referred to as PAC$^m$ - were derived to introduce free energy metrics that account for the performance of ensemble predictors, obtaining enhanced performance under misspecification. This work presents a novel robust free energy criterion that combines the generalized logarithm score function with PAC$^m$ ensemble bounds. The proposed free energy training criterion produces predictive distributions that are able to concurrently counteract the detrimental effects of model misspecification and outliers.

Leveraging Channel Noise for Sampling and Privacy via Quantized Federated Langevin Monte Carlo

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.

Training Hybrid Classical-Quantum Classifiers via Stochastic Variational Optimization

Quantum machine learning has emerged as a potential practical application of near-term quantum devices. In this work, we study a two-layer hybrid classical-quantum classifier in which a first layer of quantum stochastic neurons implementing generalized linear models (QGLMs) is followed by a second classical combining layer. The input to the first, hidden, layer is obtained via amplitude encoding in order to leverage the exponential size of the fan-in of the quantum neurons in the number of qubits per neuron. To facilitate implementation of the QGLMs, all weights and activations are binary. While the state of the art on training strategies for this class of models is limited to exhaustive search and single-neuron perceptron-like bit-flip strategies, this letter introduces a stochastic variational optimization approach that enables the joint training of quantum and classical layers via stochastic gradient descent. Experiments show the advantages of the approach for a variety of activation functions implemented by QGLM neurons.

Transfer Learning in Quantum Parametric Classifiers: An Information-Theoretic Generalization Analysis

A key step in quantum machine learning with classical inputs is the design of an embedding circuit mapping inputs to a quantum state. This paper studies a transfer learning setting in which classical-to-quantum embedding is carried out by an arbitrary parametric quantum circuit that is pre-trained based on data from a source task. At run time, the binary classifier is then optimized based on data from the target task of interest. Using an information-theoretic approach, we demonstrate that the average excess risk, or optimality gap, can be bounded in terms of two R\'enyi mutual information terms between classical input and quantum embedding under source and target tasks, as well as in terms of a measure of similarity between the source and target tasks related to the trace distance. The main theoretical results are validated on a simple binary classification example.

Adaptive Worker Grouping For Communication-Efficient and Straggler-Tolerant Distributed SGD

Wall-clock convergence time and communication load are key performance metrics for the distributed implementation of stochastic gradient descent (SGD) in parameter server settings. Communication-adaptive distributed Adam (CADA) has been recently proposed as a way to reduce communication load via the adaptive selection of workers. CADA is subject to performance degradation in terms of wall-clock convergence time in the presence of stragglers. This paper proposes a novel scheme named grouping-based CADA (G-CADA) that retains the advantages of CADA in reducing the communication load, while increasing the robustness to stragglers at the cost of additional storage at the workers. G-CADA partitions the workers into groups of workers that are assigned the same data shards. Groups are scheduled adaptively at each iteration, and the server only waits for the fastest worker in each selected group. We provide analysis and experimental results to elaborate the significant gains on the wall-clock time, as well as communication load and computation load, of G-CADA over other benchmark schemes.

Coded Consensus Monte Carlo: Robust One-Shot Distributed Bayesian Learning with Stragglers

This letter studies distributed Bayesian learning in a setting encompassing a central server and multiple workers by focusing on the problem of mitigating the impact of stragglers. The standard one-shot, or embarrassingly parallel, Bayesian learning protocol known as consensus Monte Carlo (CMC) is generalized by proposing two straggler-resilient solutions based on grouping and coding. The proposed methods, referred to as Group-based CMC (G-CMC) and Coded CMC (C-CMC), leverage redundant computing at the workers in order to enable the estimation of global posterior samples at the server based on partial outputs from the workers. Simulation results show that C-CMC may outperform G-GCMC for a small number of workers, while G-CMC is generally preferable for a larger number of workers.

Learning to Broadcast for Ultra-Reliable Communication with Differential Quality of Service via the Conditional Value at Risk

Broadcast/multicast communication systems are typically designed to optimize the outage rate criterion, which neglects the performance of the fraction of clients with the worst channel conditions. Targeting ultra-reliable communication scenarios, this paper takes a complementary approach by introducing the conditional value-at-risk (CVaR) rate as the expected rate of a worst-case fraction of clients. To support differential quality-of-service (QoS) levels in this class of clients, layered division multiplexing (LDM) is applied, which enables decoding at different rates. Focusing on a practical scenario in which the transmitter does not know the fading distribution, layer allocation is optimized based on a dataset sampled during deployment. The optimality gap caused by the availability of limited data is bounded via a generalization analysis, and the sample complexity is shown to increase as the designated fraction of worst-case clients decreases. Considering this theoretical result, meta-learning is introduced as a means to reduce sample complexity by leveraging data from previous deployments. Numerical experiments demonstrate that LDM improves spectral efficiency even for small datasets; that, for sufficiently large datasets, the proposed mirror-descent-based layer optimization scheme achieves a CVaR rate close to that achieved when the transmitter knows the fading distribution; and that meta-learning can significantly reduce data requirements.