Reliable uncertainty quantification is critical for trustworthy AI. Conformal Prediction (CP) provides prediction sets with distribution-free coverage guarantees, but its two main variants face complementary limitations. Split CP (SCP) suffers from data inefficiency due to dataset partitioning, while full CP (FCP) improves data efficiency at the cost of prohibitive retraining complexity. Recent approaches based on meta-learning or in-context learning (ICL) partially mitigate these drawbacks. However, they rely on training procedures not specifically tailored to CP, which may yield large prediction sets. We introduce an efficient FCP framework, termed enhanced ICL-based FCP (E-ICL+FCP), which employs a permutation-invariant Transformer-based ICL model trained with a CP-aware loss. By simulating the multiple retrained models required by FCP without actual retraining, E-ICL+FCP preserves coverage while markedly reducing both inefficiency and computational overhead. Experiments on synthetic and real tasks demonstrate that E-ICL+FCP attains superior efficiency-coverage trade-offs compared to existing SCP and FCP baselines.

Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications, assisting with tasks including troubleshooting, standards interpretation, and network optimization. However, their deployment in practice must balance inference cost, latency, and reliability. In this work, we study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline. In it, an efficient edge model handles routine queries, a more capable cloud model addresses complex cases, and human experts are involved only when necessary. We define a misalignment-cost constrained optimization problem, aiming to minimize average processing cost, while guaranteeing alignment of automated answers with expert judgments. We propose a statistically rigorous threshold selection method based on multiple hypothesis testing (MHT) for a query processing mechanism based on knowledge and confidence tests. The approach provides finite-sample guarantees on misalignment risk. Experiments on the TeleQnA dataset –a telecom-specific benchmark – demonstrate that the proposed method achieves superior cost-efficiency compared to conventional cascaded baselines, while ensuring reliability at prescribed confidence levels.

We introduce adaptive learn-then-test (aLTT), an efficient hyperparameter selection procedure that provides finite-sample statistical guarantees on the population risk of AI models. Unlike the existing learn-then-test (LTT) technique, which relies on conventional p-value-based multiple hypothesis testing (MHT), aLTT implements sequential data-dependent MHT with early termination by leveraging e-processes. As a result, aLTT can reduce the number of testing rounds, making it particularly well-suited for scenarios in which testing is costly or presents safety risks. Apart from maintaining statistical validity, in applications such as online policy selection for offline reinforcement learning and prompt engineering, aLTT is shown to achieve the same performance as LTT while requiring only a fraction of the testing rounds.

Deploying artificial intelligence (AI) models on edge devices involves a delicate balance between meeting stringent complexity constraints, such as limited memory and energy resources, and ensuring reliable performance in sensitive decision-making tasks. One way to enhance reliability is through uncertainty quantification via Bayesian inference. This approach, however, typically necessitates maintaining and running multiple models in an ensemble, which may exceed the computational limits of edge devices. This paper introduces a low-complexity methodology to address this challenge by distilling calibration information from a more complex model. In an offline phase, predictive probabilities generated by a high-complexity cloud-based model are leveraged to determine a threshold based on the typical divergence between the cloud and edge models. At run time, this threshold is used to construct credal sets – ranges of predictive probabilities that are guaranteed, with a user-selected confidence level, to include the predictions of the cloud model. The credal sets are obtained through thresholding of a divergence measure in the simplex of predictive probabilities. Experiments on visual and language tasks demonstrate that the proposed approach, termed Conformalized Distillation for Credal Inference (CD-CI), significantly improves calibration performance compared to low-complexity Bayesian methods, such as Laplace approximation, making it a practical and efficient solution for edge AI deployments.

Predictive models are often required to produce reliable predictions under statistical conditions that are not matched to the training data. A common type of training-testing mismatch is covariate shift, where the conditional distribution of the target variable given the input features remains fixed, while the marginal distribution of the inputs changes. Weighted conformal risk control (W-CRC) uses data collected during the training phase to convert point predictions into prediction sets with valid risk guarantees at test time despite the presence of a covariate shift. However, while W-CRC provides statistical reliability, its efficiency - measured by the size of the prediction sets - can only be assessed at test time. In this work, we relate the generalization properties of the base predictor to the efficiency of W-CRC under covariate shifts. Specifically, we derive a bound on the inefficiency of the W-CRC predictor that depends on algorithmic hyperparameters and task-specific quantities available at training time. This bound offers insights on relationships between the informativeness of the prediction sets, the extent of the covariate shift, and the size of the calibration and training sets. Experiments on fingerprinting-based localization validate the theoretical results.

Selecting artificial intelligence (AI) models, such as large language models (LLMs), from multiple candidates requires accurate performance estimation. This is ideally achieved through empirical evaluations involving abundant real-world data. However, such evaluations are costly and impractical at scale. To address this challenge, autoevaluation methods leverage synthetic data produced by automated evaluators, such as LLMs-as-judges, reducing variance but potentially introducing bias. Recent approaches have employed semi-supervised prediction-powered inference ($\texttt{PPI}$) to correct for the bias of autoevaluators. However, the use of autoevaluators may lead in practice to a degradation in sample efficiency compared to conventional methods using only real-world data. In this paper, we propose $\texttt{R-AutoEval+}$, a novel framework that provides finite-sample reliability guarantees on the model evaluation, while also ensuring an enhanced (or at least no worse) sample efficiency compared to conventional methods. The key innovation of $\texttt{R-AutoEval+}$ is an adaptive construction of the model evaluation variable, which dynamically tunes its reliance on synthetic data, reverting to conventional methods when the autoevaluator is insufficiently accurate. Experiments on the use of LLMs-as-judges for the optimization of quantization settings for the weights of an LLM, for prompt design in LLMs, and for test-time reasoning budget allocation in LLMs confirm the reliability and efficiency of $\texttt{R-AutoEval+}$.

In modern wireless network architectures, such as O-RAN, artificial intelligence (AI)-based applications are deployed at intelligent controllers to carry out functionalities like scheduling or power control. The AI “apps” are selected on the basis of contextual information such as network conditions, topology, traffic statistics, and design goals. The mapping between context and AI model parameters is ideally done in a zero-shot fashion via an automatic model selection (AMS) mapping that leverages only contextual information without requiring any current data. This paper introduces a general methodology for the online optimization of AMS mappings. Optimizing an AMS mapping is challenging, as it requires exposure to data collected from many different contexts. Therefore, if carried out online, this initial optimization phase would be extremely time consuming. A possible solution is to leverage a digital twin of the physical system to generate synthetic data from multiple simulated contexts. However, given that the simulator at the digital twin is imperfect, a direct use of simulated data for the optimization of the AMS mapping would yield poor performance when tested in the real system. This paper proposes a novel method for the online optimization of AMS mapping that corrects for the bias of the simulator by means of limited real data collected from the physical system. Experimental results for a graph neural network-based power control app demonstrate the significant advantages of the proposed approach.

Conformal risk control (CRC) is a recently proposed technique that applies post-hoc to a conventional point predictor to provide calibration guarantees. Generalizing conformal prediction (CP), with CRC, calibration is ensured for a set predictor that is extracted from the point predictor to control a risk function such as the probability of miscoverage or the false negative rate. The original CRC requires the available data set to be split between training and validation data sets. This can be problematic when data availability is limited, resulting in inefficient set predictors. In this paper, a novel CRC method is introduced that is based on cross-validation, rather than on validation as the original CRC. The proposed cross-validation CRC (CV-CRC) extends a version of the jackknife-minmax from CP to CRC, allowing for the control of a broader range of risk functions. CV-CRC is proved to offer theoretical guarantees on the average risk of the set predictor. Furthermore, numerical experiments show that CV-CRC can reduce the average set size with respect to CRC when the available data are limited.

The safe integration of machine learning modules in decision-making processes hinges on their ability to quantify uncertainty. A popular technique to achieve this goal is conformal prediction (CP), which transforms an arbitrary base predictor into a set predictor with coverage guarantees. While CP certifies the predicted set to contain the target quantity with a user-defined tolerance, it does not provide control over the average size of the predicted sets, i.e., over the informativeness of the prediction. In this work, a theoretical connection is established between the generalization properties of the base predictor and the informativeness of the resulting CP prediction sets. To this end, an upper bound is derived on the expected size of the CP set predictor that builds on generalization error bounds for the base predictor. The derived upper bound provides insights into the dependence of the average size of the CP set predictor on the amount of calibration data, the target reliability, and the generalization performance of the base predictor. The theoretical insights are validated using simple numerical regression and classification tasks.

Conventional frequentist learning is known to yield poorly calibrated models that fail to reliably quantify the uncertainty of their decisions. Bayesian learning can improve calibration, but formal guarantees apply only under restrictive assumptions about correct model specification. Conformal prediction (CP) offers a general framework for the design of set predictors with calibration guarantees that hold regardless of the underlying data generation mechanism. However, when training data are limited, CP tends to produce large, and hence uninformative, predicted sets. This paper introduces a novel meta-learning solution that aims at reducing the set prediction size. Unlike prior work, the proposed meta-learning scheme, referred to as meta-XB, i) builds on cross-validation-based CP, rather than the less efficient validation-based CP; and ii) preserves formal per-task calibration guarantees, rather than less stringent task-marginal guarantees. Finally, meta-XB is extended to adaptive non-conformal scores, which are shown empirically to further enhance marginal per-input calibration.

The increasing adoption of Artificial Intelligence (AI) in engineering problems calls for the development of calibration methods capable of offering robust statistical reliability guarantees. The calibration of black box AI models is carried out via the optimization of hyperparameters dictating architecture, optimization, and/or inference configuration. Prior work has introduced learn-then-test (LTT), a calibration procedure for hyperparameter optimization (HPO) that provides statistical guarantees on average performance measures. Recognizing the importance of controlling risk-aware objectives in engineering contexts, this work introduces a variant of LTT that is designed to provide statistical guarantees on quantiles of a risk measure. We illustrate the practical advantages of this approach by applying the proposed algorithm to a radio access scheduling problem.

Standard Bayesian learning is known to have suboptimal generalization capabilities under misspecification and in the presence of outliers. Probably approximately correct (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 are affected by outliers. In recent work, PAC-Bayes bounds-referred to as PACm-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 PACm ensemble bounds. The proposed free energy training criterion produces predictive distributions that are able to concurrently counteract the detrimental effects of misspecification-with respect to both likelihood and prior distribution-and outliers.

Under frequency-selective multi-path channel environment, delayed copies of the transmitted symbols are summed up to form a received signal. In order to remove this intersymbol interference (ISI), linear minimum mean-square error (LMMSE) equalizer can be applied to the received signal to reconstruct the transmitted symbols. While being an optimal linear filter, the LMMSE equalizer ideally requires infinite length of the received signal, which is infeasible in practice. In order to mitigate this limitation of linear filters, we propose to utilize neural networks for equalization, referred to as neural filters. Numerical results verify that, given with enough pilot data, the proposed neural filter outperforms the optimal LMMSE equalizer that uses perfect knowledge on the channel realization vector.

Artificial Intelligent (AI) tools can be useful to address model deficits in the design of communication systems. However, conventional learning-based AI algorithms yield poorly calibrated decisions, unabling to quantify their outputs uncertainty. While Bayesian learning can enhance calibration by capturing epistemic uncertainty caused by limited data availability, formal calibration guarantees only hold under strong assumptions about the ground-truth, unknown, data generation mechanism. We propose to leverage the conformal prediction framework to obtain data-driven set predictions whose calibration properties hold irrespective of the data distribution. Specifically, we investigate the design of baseband demodulators in the presence of hard-to-model nonlinearities such as hardware imperfections, and propose set-based demodulators based on conformal prediction. Numerical results confirm the theoretical validity of the proposed demodulators, and bring insights into their average prediction set size efficiency.

Unmanned aerial base stations (UABSs) can be deployed in vehicular wireless networks to support applications such as extended sensing via vehicle-to-everything (V2X) services. A key problem in such systems is designing algorithms that can efficiently optimize the trajectory of the UABS in order to maximize coverage. In existing solutions, such optimization is carried out from scratch for any new traffic configuration, often by means of conventional reinforcement learning (RL). In this paper, we propose the use of continual meta-RL as a means to transfer information from previously experienced traffic configurations to new conditions, with the goal of reducing the time needed to optimize the UABS's policy. Adopting the Continual Meta Policy Search (CoMPS) strategy, we demonstrate significant efficiency gains as compared to conventional RL, as well as to naive transfer learning methods.

Federated learning (FL) aims at optimizing a shared global model over multiple edge devices without transmitting (private) data to the central server. While it is theoretically well-known that FL yields an optimal model – centrally trained model assuming availability of all the edge device data at the central server – under mild condition, in practice, it often requires massive amount of iterations until convergence, especially under presence of statistical/computational heterogeneity. This paper utilizes cyclic learning rate at the server side to reduce the number of training iterations with increased performance without any additional computational costs for both the server and the edge devices. Numerical results validate that, simply plugging-in the proposed cyclic aggregation to the existing FL algorithms effectively reduces the number of training iterations with improved performance.

Increasing communication bandwidth is a highly effective method for improving communication system throughput. However, the sub-6GHz frequency band is already heavily utilized, which has led to the exploration of higher frequency bands such as sub-terahertz (sub-THz) communication as a key technology for the upcoming 6G era. Unfortunately, sub-THz channels tend to have only line-of-sight (LoS) components due to reflection losses, making it challenging to achieve multiplexing gain through spatial dimension. This paper investigates the practical implications of using orthogonal angular momentum (OAM) signals for multiplexing in LoS scenarios. While being a well-known fact that independent transmit signals conveyed on orthogonal OAM modes keep independence at the receiver side under a perfectly aligned system, here we focus on misaligned system in which inter-mode-interference (IMI) breaks such independence. Inspired by recent advancements in MIMO detection, particularly deep soft interference cancellation (DeepSIC), we propose a hybrid model-based/data-driven detector for misaligned OAM system that aims at achieving minimal symbol error rate via mitigating IMI. Experimental results demonstrate that the proposed detector, named OAM-DeepSIC, outperforms conventional detectors with minimal computational cost.

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.

The overall predictive uncertainty of a trained predictor can be decomposed into separate contributions due to epistemic and aleatoric uncertainty. Under a Bayesian formulation, assuming a well-specified model, the two contributions can be exactly expressed (for the log-loss) or bounded (for more general losses) in terms of information-theoretic quantities (Xu and Raginsky [2020]). This paper addresses the study of epistemic uncertainty within an information-theoretic framework in the broader setting of Bayesian meta-learning. A general hierarchical Bayesian model is assumed in which hyperparameters determine the per-task priors of the model parameters. Exact characterizations (for the log-loss) and bounds (for more general losses) are derived for the epistemic uncertainty – quantified by the minimum excess meta-risk (MEMR)– of optimal meta-learning rules. This characterization is leveraged to bring insights into the dependence of the epistemic uncertainty on the number of tasks and on the amount of per-task training data. Experiments are presented that use the proposed information-theoretic bounds, evaluated via neural mutual information estimators, to compare the performance of conventional learning and meta-learning as the number of meta-learning tasks increases.

Predicting fading channels is a classical problem with a vast array of applications, including as an enabler of artificial intelligence (AI)-based proactive resource allocation for cellular networks. Under the assumption that the fading channel follows a stationary complex Gaussian process, as for Rayleigh and Rician fading models, the optimal predictor is linear, and it can be directly computed from the Doppler spectrum via standard linear minimum mean squared error (LMMSE) estimation. However, in practice, the Doppler spectrum is unknown, and the predictor has only access to a limited time series of estimated channels. This paper proposes to leverage meta-learning in order to mitigate the requirements in terms of training data for channel fading prediction. Specifically, it first develops an offline low-complexity solution based on linear filtering via a meta-trained quadratic regularization. Then, an online method is proposed based on gradient descent and equilibrium propagation (EP). Numerical results demonstrate the advantages of the proposed approach, showing its capacity to approach the genie-aided LMMSE solution with a small number of training data points.

Whenever wireless communication link becomes a unique communication means, ensuring security is just as important as achieving fast and reliable communication especially for military and medical systems. A common approach for secure wireless communication is via encryption of the information but this may fail to provide complete security (e.g., vulnerable to side-channel attack) especially when it comes with computation-limited scenarios such as Internet of Things (IoT) case. A simpler, yet powerful alternative technique to improve security is by preventing eavesdroppers from knowing correct modulation and coding (MCS) scheme. In traditional wireless communication systems, this MCS information can be secured based on sophisticate design of mutually cooperative strategies between the transmitter and the receiver. However, for deep learning (DL)-based wireless communication systems, this cooperation can be significantly simplified by just adding a well-designed adversarial signal to the transmitted signal. In this paper, we propose a novel, transferable adversarial signal design that simultaneously prevents non-cooperative eavesdroppers from achieving correct modulation scheme while ensuring the intended, cooperative receiver's correct acquisition of the modulation scheme. Extensive numerical results validate secrecy of the proposed scheme along with transferability.

When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder. An important limitation of the approach is that training should be generally carried out from scratch for each new channel. To cope with this problem, prior works considered joint training over multiple channels with the aim of finding a single pair of encoder and decoder that works well on a class of channels. As a result, joint training ideally mimics the operation of non-coherent transmission schemes. In this paper, we propose to obviate the limitations of joint training via meta-learning: Rather than training a common model for all channels, meta-learning finds a common initialization vector that enables fast training on any channel. The approach is validated via numerical results, demonstrating significant training speed-ups, with effective encoders and decoders obtained with as little as one iteration of Stochastic Gradient Descent.

In this paper, for cloud-radio access network (C-RAN) architecture which consists of the cloud and base stations (BSs) via dedicated fronthaul link, we investigate the energy efficiency for cloud processing at the cloud and edge processing at each BS. For cloud processing, we reflect the outdated channel state information (CSI) and additional power consumption for the centralized processing. For edge processing, each RRH is allowed to perform baseband processing based on local, but timely CSI. Thus, we reflect the degradation of spectral efficiency induced by inter-cell interference to our energy efficiency model. Furthermore, we propose an RRH selection algorithm for cloud and edge processing to enhance the energy efficiency. Simulation results show that there certainly exists the regime that the edge processing outperforms than the cloud processing. Moreover, we observe that, by means of our proposed algorithm, the energy efficiency is enhanced, especially in cloud processing.

The dynamic scheduling of ultra-reliable and low-latency traffic (URLLC) in the uplink can significantly enhance the efficiency of coexisting services, such as enhanced mobile broadband (eMBB) devices, by only allocating resources when necessary. The main challenge is posed by the uncertainty in the process of URLLC packet generation, which mandates the use of predictors for URLLC traffic in the coming frames. In practice, such prediction may overestimate or underestimate the amount of URLLC data to be generated, yielding either an excessive or an insufficient amount of resources to be pre-emptively allocated for URLLC packets. In this paper, we introduce a novel scheduler for URLLC packets that provides formal guarantees on reliability and latencyirrespective of the quality of the URLLC traffic predictor. The proposed method leverages recent advances inonline conformal prediction (CP), and follows the principle of dynamically adjusting the amount of allocated resources so as to meet reliability and latency requirements set by the designer.