Towards Efficient and Trustworthy AI Through Hardware-Algorithm-Communication Co-Design

Artificial intelligence (AI) algorithms based on neural networks have been designed for decades with the goal of maximising some measure of accuracy. This has led to two undesired effects. First, model complexity has risen exponentially when measured in terms of computation and memory requirements. Second, state-of-the-art AI models are largely incapable of providing trustworthy measures of their uncertainty, possibly `hallucinating' their answers and discouraging their adoption for decision-making in sensitive applications. With the goal of realising efficient and trustworthy AI, in this paper we highlight research directions at the intersection of hardware and software design that integrate physical insights into computational substrates, neuroscientific principles concerning efficient information processing, information-theoretic results on optimal uncertainty quantification, and communication-theoretic guidelines for distributed processing. Overall, the paper advocates for novel design methodologies that target not only accuracy but also uncertainty quantification, while leveraging emerging computing hardware architectures that move beyond the traditional von Neumann digital computing paradigm to embrace in-memory, neuromorphic, and quantum computing technologies. An important overarching principle of the proposed approach is to view the stochasticity inherent in the computational substrate and in the communication channels between processors as a resource to be leveraged for the purpose of representing and processing classical and quantum uncertainty.

Statistical Complexity of Quantum Learning

Recent years have seen significant activity on the problem of using data for the purpose of learning properties of quantum systems or of processing classical or quantum data via quantum computing. As in classical learning, quantum learning problems involve settings in which the mechanism generating the data is unknown, and the main goal of a learning algorithm is to ensure satisfactory accuracy levels when only given access to data and, possibly, side information such as expert knowledge. This article reviews the complexity of quantum learning using information-theoretic techniques by focusing on data complexity, copy complexity, and model complexity. Copy complexity arises from the destructive nature of quantum measurements, which irreversibly alter the state to be processed, limiting the information that can be extracted about quantum data. For example, in a quantum system, unlike in classical machine learning, it is generally not possible to evaluate the training loss simultaneously on multiple hypotheses using the same quantum data. To make the paper self-contained and approachable by different research communities, we provide extensive background material on classical results from statistical learning theory, as well as on the distinguishability of quantum states. Throughout, we highlight the differences between quantum and classical learning by addressing both supervised and unsupervised learning, and we provide extensive pointers to the literature.

Energy-Efficient On-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing

The latest satellite communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic. As pure optimization-based solutions have shown to be computationally tedious and to lack flexibility, machine learning (ML)-based methods have emerged as promising alternatives. We investigate the application of energy-efficient brain-inspired ML models for on-board radio resource management. Apart from software simulation, we report extensive experimental results leveraging the recently released Intel Loihi 2 chip. To benchmark the performance of the proposed model, we implement conventional convolutional neural networks (CNN) on a Xilinx Versal VCK5000, and provide a detailed comparison of accuracy, precision, recall, and energy efficiency for different traffic demands. Most notably, for relevant workloads, spiking neural networks (SNNs) implemented on Loihi 2 yield higher accuracy, while reducing power consumption by more than 100$\times$ as compared to the CNN-based reference platform. Our findings point to the significant potential of neuromorphic computing and SNNs in supporting on-board SatCom operations, paving the way for enhanced efficiency and sustainability in future SatCom systems.

Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Prediction

Consider a setting in which devices and a server share a pre-trained model. The server wishes to make an inference on a new input given the model. Devices have access to data, previously not used for training, and can communicate to the server over a common wireless channel. If the devices have no access to the new input, can communication from devices to the server enhance the quality of the inference decision at the server? Recent work has introduced federated conformal prediction (CP), which leverages devices-to-server communication to improve the reliability of the server's decision. With federated CP, devices communicate to the server information about the loss accrued by the shared pre-trained model on the local data, and the server leverages this information to calibrate a decision interval, or set, so that it is guaranteed to contain the correct answer with a pre-defined target reliability level. Previous work assumed noise-free communication, whereby devices can communicate a single real number to the server. In this paper, we study for the first time federated CP in a wireless setting. We introduce a novel protocol, termed wireless federated conformal prediction (WFCP), which builds on type-based multiple access (TBMA) and on a novel quantile correction strategy. WFCP is proved to provide formal reliability guarantees in terms of coverage of the predicted set produced by the server. Using numerical results, we demonstrate the significant advantages of WFCP against digital implementations of existing federated CP schemes, especially in regimes with limited communication resources and/or large number of devices.

Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction

Black-box zero-th order optimization is a central primitive for applications in fields as diverse as finance, physics, and engineering. In a common formulation of this problem, a designer sequentially attempts candidate solutions, receiving noisy feedback on the value of each attempt from the system. In this paper, we study scenarios in which feedback is also provided on the safety of the attempted solution, and the optimizer is constrained to limit the number of unsafe solutions that are tried throughout the optimization process. Focusing on methods based on Bayesian optimization (BO), prior art has introduced an optimization scheme -- referred to as SAFEOPT -- that is guaranteed not to select any unsafe solution with a controllable probability over feedback noise as long as strict assumptions on the safety constraint function are met. In this paper, a novel BO-based approach is introduced that satisfies safety requirements irrespective of properties of the constraint function. This strong theoretical guarantee is obtained at the cost of allowing for an arbitrary, controllable but non-zero, rate of violation of the safety constraint. The proposed method, referred to as SAFE-BOCP, builds on online conformal prediction (CP) and is specialized to the cases in which feedback on the safety constraint is either noiseless or noisy. Experimental results on synthetic and real-world data validate the advantages and flexibility of the proposed SAFE-BOCP.

Convergence Analysis of Over-the-Air FL with Compression and Power Control via Clipping

One of the key challenges towards the deployment of over-the-air federated learning (AirFL) is the design of mechanisms that can comply with the power and bandwidth constraints of the shared channel, while causing minimum deterioration to the learning performance as compared to baseline noiseless implementations. For additive white Gaussian noise (AWGN) channels with instantaneous per-device power constraints, prior work has demonstrated the optimality of a power control mechanism based on norm clipping. This was done through the minimization of an upper bound on the optimality gap for smooth learning objectives satisfying the Polyak-{\L}ojasiewicz (PL) condition. In this paper, we make two contributions to the development of AirFL based on norm clipping, which we refer to as AirFL-Clip. First, we provide a convergence bound for AirFLClip that applies to general smooth and non-convex learning objectives. Unlike existing results, the derived bound is free from run-specific parameters, thus supporting an offline evaluation. Second, we extend AirFL-Clip to include Top-k sparsification and linear compression. For this generalized protocol, referred to as AirFL-Clip-Comp, we derive a convergence bound for general smooth and non-convex learning objectives. We argue, and demonstrate via experiments, that the only time-varying quantities present in the bound can be efficiently estimated offline by leveraging the well-studied properties of sparse recovery algorithms.

SpikeCP: Delay-Adaptive Reliable Spiking Neural Networks via Conformal Prediction

Spiking neural networks (SNNs) process time-series data via internal event-driven neural dynamics whose energy consumption depends on the number of spikes exchanged between neurons over the course of the input presentation. In typical implementations of an SNN classifier, decisions are produced after the entire input sequence has been processed, resulting in latency and energy consumption levels that are fairly uniform across inputs. Recently introduced delay-adaptive SNNs tailor the inference latency -- and, with it, the energy consumption -- to the difficulty of each example, by producing an early decision when the SNN model is sufficiently ``confident''. In this paper, we start by observing that, as an SNN processes input samples, its classification decisions tend to be first under-confident and then over-confident with respect to the decision's ground-truth, unknown, test accuracy. This makes it difficult to determine a stopping time that ensures a desired level of accuracy. To address this problem, we introduce a novel delay-adaptive SNN-based inference methodology that, wrapping around any pre-trained SNN classifier, provides guaranteed reliability for the decisions produced at input-dependent stopping times. The approach entails minimal added complexity as compared to the underlying SNN, requiring only thresholding and counting operations at run time, and it leverages tools from conformal prediction (CP).

Calibration-Aware Bayesian Learning

Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions. In order to improve the quality of the confidence levels, also known as calibration, of a model, common approaches entail the addition of either data-dependent or data-independent regularization terms to the training loss. Data-dependent regularizers have been recently introduced in the context of conventional frequentist learning to penalize deviations between confidence and accuracy. In contrast, data-independent regularizers are at the core of Bayesian learning, enforcing adherence of the variational distribution in the model parameter space to a prior density. The former approach is unable to quantify epistemic uncertainty, while the latter is severely affected by model misspecification. In light of the limitations of both methods, this paper proposes an integrated framework, referred to as calibration-aware Bayesian neural networks (CA-BNNs), that applies both regularizers while optimizing over a variational distribution as in Bayesian learning. Numerical results validate the advantages of the proposed approach in terms of expected calibration error (ECE) and reliability diagrams.

Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics

The recent development of scalable Bayesian inference methods has renewed interest in the adoption of Bayesian learning as an alternative to conventional frequentist learning that offers improved model calibration via uncertainty quantification. Recently, federated averaging Langevin dynamics (FALD) was introduced as a variant of federated averaging that can efficiently implement distributed Bayesian learning in the presence of noiseless communications. In this paper, we propose wireless FALD (WFALD), a novel protocol that realizes FALD in wireless systems by integrating over-the-air computation and channel-driven sampling for Monte Carlo updates. Unlike prior work on wireless Bayesian learning, WFALD enables (\emph{i}) multiple local updates between communication rounds; and (\emph{ii}) stochastic gradients computed by mini-batch. A convergence analysis is presented in terms of the 2-Wasserstein distance between the samples produced by WFALD and the targeted global posterior distribution. Analysis and experiments show that, when the signal-to-noise ratio is sufficiently large, channel noise can be fully repurposed for Monte Carlo sampling, thus entailing no loss in performance.

Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning

Quantum machine learning is a promising programming paradigm for the optimization of quantum algorithms in the current era of noisy intermediate scale quantum (NISQ) computers. A fundamental challenge in quantum machine learning is generalization, as the designer targets performance under testing conditions, while having access only to limited training data. Existing generalization analyses, while identifying important general trends and scaling laws, cannot be used to assign reliable and informative "error bars" to the decisions made by quantum models. In this article, we propose a general methodology that can reliably quantify the uncertainty of quantum models, irrespective of the amount of training data, of the number of shots, of the ansatz, of the training algorithm, and of the presence of quantum hardware noise. The approach, which builds on probabilistic conformal prediction, turns an arbitrary, possibly small, number of shots from a pre-trained quantum model into a set prediction, e.g., an interval, that provably contains the true target with any desired coverage level. Experimental results confirm the theoretical calibration guarantees of the proposed framework, referred to as quantum conformal prediction.