Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference

The application of artificial intelligence (AI) models in fields such as engineering is limited by the known difficulty of quantifying the reliability of an AI's decision. A well-calibrated AI model must correctly report its accuracy on in-distribution (ID) inputs, while also enabling the detection of out-of-distribution (OOD) inputs. A conventional approach to improve calibration is the application of Bayesian ensembling. However, owing to computational limitations and model misspecification, practical ensembling strategies do not necessarily enhance calibration. This paper proposes an extension of variational inference (VI)-based Bayesian learning that integrates calibration regularization for improved ID performance, confidence minimization for OOD detection, and selective calibration to ensure a synergistic use of calibration regularization and confidence minimization. The scheme is constructed successively by first introducing calibration-regularized Bayesian learning (CBNN), then incorporating out-of-distribution confidence minimization (OCM) to yield CBNN-OCM, and finally integrating also selective calibration to produce selective CBNN-OCM (SCBNN-OCM). Selective calibration rejects inputs for which the calibration performance is expected to be insufficient. Numerical results illustrate the trade-offs between ID accuracy, ID calibration, and OOD calibration attained by both frequentist and Bayesian learning methods. Among the main conclusions, SCBNN-OCM is seen to achieve best ID and OOD performance as compared to existing state-of-the-art approaches at the cost of rejecting a sufficiently large number of inputs.

Cell-Free Multi-User MIMO Equalization via In-Context Learning

Large pre-trained sequence models, such as transformers, excel as few-shot learners capable of in-context learning (ICL). In ICL, a model is trained to adapt its operation to a new task based on limited contextual information, typically in the form of a few training examples for the given task. Previous work has explored the use of ICL for channel equalization in single-user multi-input and multiple-output (MIMO) systems. In this work, we demonstrate that ICL can be also used to tackle the problem of multi-user equalization in cell-free MIMO systems with limited fronthaul capacity. In this scenario, a task is defined by channel statistics, signal-to-noise ratio, and modulation schemes. The context encompasses the users' pilot sequences, the corresponding quantized received signals, and the current received data signal. Different prompt design strategies are proposed and evaluated that encompass also large-scale fading and modulation information. Experiments demonstrate that ICL-based equalization provides estimates with lower mean squared error as compared to the linear minimum mean squared error equalizer, especially in the presence of limited fronthaul capacity and pilot contamination.

Neuromorphic In-Context Learning for Energy-Efficient MIMO Symbol Detection

In-context learning (ICL), a property demonstrated by transformer-based sequence models, refers to the automatic inference of an input-output mapping based on examples of the mapping provided as context. ICL requires no explicit learning, i.e., no explicit updates of model weights, directly mapping context and new input to the new output. Prior work has proved the usefulness of ICL for detection in MIMO channels. In this setting, the context is given by pilot symbols, and ICL automatically adapts a detector, or equalizer, to apply to newly received signals. However, the implementation tested in prior art was based on conventional artificial neural networks (ANNs), which may prove too energy-demanding to be run on mobile devices. This paper evaluates a neuromorphic implementation of the transformer for ICL-based MIMO detection. This approach replaces ANNs with spiking neural networks (SNNs), and implements the attention mechanism via stochastic computing, requiring no multiplications, but only logical AND operations and counting. When using conventional digital CMOS hardware, the proposed implementation is shown to preserve accuracy, with a reduction in power consumption ranging from $5.4\times$ to $26.8\times$, depending on the model sizes, as compared to ANN-based implementations.

Neuromorphic Split Computing with Wake-Up Radios: Architecture and Design via Digital Twinning

Neuromorphic computing leverages the sparsity of temporal data to reduce processing energy by activating a small subset of neurons and synapses at each time step. When deployed for split computing in edge-based systems, remote neuromorphic processing units (NPUs) can reduce the communication power budget by communicating asynchronously using sparse impulse radio (IR) waveforms. This way, the input signal sparsity translates directly into energy savings both in terms of computation and communication. However, with IR transmission, the main contributor to the overall energy consumption remains the power required to maintain the main radio on. This work proposes a novel architecture that integrates a wake-up radio mechanism within a split computing system consisting of remote, wirelessly connected, NPUs. A key challenge in the design of a wake-up radio-based neuromorphic split computing system is the selection of thresholds for sensing, wake-up signal detection, and decision making. To address this problem, as a second contribution, this work proposes a novel methodology that leverages the use of a digital twin (DT), i.e., a simulator, of the physical system, coupled with a sequential statistical testing approach known as Learn Then Test (LTT) to provide theoretical reliability guarantees. The proposed DT-LTT methodology is broadly applicable to other design problems, and is showcased here for neuromorphic communications. Experimental results validate the design and the analysis, confirming the theoretical reliability guarantees and illustrating trade-offs among reliability, energy consumption, and informativeness of the decisions.

Neuromorphic Wireless Device-Edge Co-Inference via the Directed Information Bottleneck

An important use case of next-generation wireless systems is device-edge co-inference, where a semantic task is partitioned between a device and an edge server. The device carries out data collection and partial processing of the data, while the remote server completes the given task based on information received from the device. It is often required that processing and communication be run as efficiently as possible at the device, while more computing resources are available at the edge. To address such scenarios, we introduce a new system solution, termed neuromorphic wireless device-edge co-inference. According to it, the device runs sensing, processing, and communication units using neuromorphic hardware, while the server employs conventional radio and computing technologies. The proposed system is designed using a transmitter-centric information-theoretic criterion that targets a reduction of the communication overhead, while retaining the most relevant information for the end-to-end semantic task of interest. Numerical results on standard data sets validate the proposed architecture, and a preliminary testbed realization is reported.

Cell-Free MIMO Perceptive Mobile Networks: Cloud vs. Edge Processing

Perceptive mobile networks implement sensing and communication by reusing existing cellular infrastructure. Cell-free multiple-input multiple-output, thanks to the cooperation among distributed access points, supports the deployment of multistatic radar sensing, while providing high spectral efficiency for data communication services. To this end, the distributed access points communicate over fronthaul links with a central processing unit acting as a cloud processor. This work explores four different types of PMN uplink solutions based on Cell-free multiple-input multiple-output, in which the sensing and decoding functionalities are carried out at either cloud or edge. Accordingly, we investigate and compare joint cloud-based decoding and sensing (CDCS), hybrid cloud-based decoding and edge-based sensing (CDES), hybrid edge-based decoding and cloud-based sensing (EDCS) and edge-based decoding and sensing (EDES). In all cases, we target a unified design problem formulation whereby the fronthaul quantization of signals received in the training and data phases are jointly designed to maximize the achievable rate under sensing requirements and fronthaul capacity constraints. Via numerical results, the four implementation scenarios are compared as a function of the available fronthaul resources by highlighting the relative merits of edge- and cloud-based sensing and communications. This study provides guidelines on the optimal functional allocation in fronthaul-constrained networks implementing integrated sensing and communications.

CSI Transfer From Sub-6G to mmWave: Reduced-Overhead Multi-User Hybrid Beamforming

Hybrid beamforming is vital in modern wireless systems, especially for massive MIMO and millimeter-wave deployments, offering efficient directional transmission with reduced hardware complexity. However, effective beamforming in multi-user scenarios relies heavily on accurate channel state information, the acquisition of which often incurs excessive pilot overhead, degrading system performance. To address this and inspired by the spatial congruence between sub-6GHz (sub-6G) and mmWave channels, we propose a Sub-6G information Aided Multi-User Hybrid Beamforming (SA-MUHBF) framework, avoiding excessive use of pilots. SA-MUHBF employs a convolutional neural network to predict mmWave beamspace from sub-6G channel estimate, followed by a novel multi-layer graph neural network for analog beam selection and a linear minimum mean-square error algorithm for digital beamforming. Numerical results demonstrate that SA-MUHBF efficiently predicts the mmWave beamspace representation and achieves superior spectrum efficiency over state-of-the-art benchmarks. Moreover, SA-MUHBF demonstrates robust performance across varied sub-6G system configurations and exhibits strong generalization to unseen scenarios.

Multi-Fidelity Bayesian Optimization With Across-Task Transferable Max-Value Entropy Search

In many applications, ranging from logistics to engineering, a designer is faced with a sequence of optimization tasks for which the objectives are in the form of black-box functions that are costly to evaluate. For example, the designer may need to tune the hyperparameters of neural network models for different learning tasks over time. Rather than evaluating the objective function for each candidate solution, the designer may have access to approximations of the objective functions, for which higher-fidelity evaluations entail a larger cost. Existing multi-fidelity black-box optimization strategies select candidate solutions and fidelity levels with the goal of maximizing the information accrued about the optimal value or solution for the current task. Assuming that successive optimization tasks are related, this paper introduces a novel information-theoretic acquisition function that balances the need to acquire information about the current task with the goal of collecting information transferable to future tasks. The proposed method includes shared inter-task latent variables, which are transferred across tasks by implementing particle-based variational Bayesian updates. Experimental results across synthetic and real-world examples reveal that the proposed provident acquisition strategy that caters to future tasks can significantly improve the optimization efficiency as soon as a sufficient number of tasks is processed.

Uncertainty, Calibration, and Membership Inference Attacks: An Information-Theoretic Perspective

In a membership inference attack (MIA), an attacker exploits the overconfidence exhibited by typical machine learning models to determine whether a specific data point was used to train a target model. In this paper, we analyze the performance of the state-of-the-art likelihood ratio attack (LiRA) within an information-theoretical framework that allows the investigation of the impact of the aleatoric uncertainty in the true data generation process, of the epistemic uncertainty caused by a limited training data set, and of the calibration level of the target model. We compare three different settings, in which the attacker receives decreasingly informative feedback from the target model: confidence vector (CV) disclosure, in which the output probability vector is released; true label confidence (TLC) disclosure, in which only the probability assigned to the true label is made available by the model; and decision set (DS) disclosure, in which an adaptive prediction set is produced as in conformal prediction. We derive bounds on the advantage of an MIA adversary with the aim of offering insights into the impact of uncertainty and calibration on the effectiveness of MIAs. Simulation results demonstrate that the derived analytical bounds predict well the effectiveness of MIAs.

Stochastic Spiking Attention: Accelerating Attention with Stochastic Computing in Spiking Networks

Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention mechanism using spiking signals on general-purpose computing platforms remains inefficient. In this paper, we propose a novel framework leveraging stochastic computing (SC) to effectively execute the dot-product attention for SNN-based Transformers. We demonstrate that our approach can achieve high classification accuracy ($83.53\%$) on CIFAR-10 within 10 time steps, which is comparable to the performance of a baseline artificial neural network implementation ($83.66\%$). We estimate that the proposed SC approach can lead to over $6.3\times$ reduction in computing energy and $1.7\times$ reduction in memory access costs for a digital CMOS-based ASIC design. We experimentally validate our stochastic attention block design through an FPGA implementation, which is shown to achieve $48\times$ lower latency as compared to a GPU implementation, while consuming $15\times$ less power.