Online Prediction of Stochastic Sequences with High Probability Regret Bounds

We revisit the classical problem of universal prediction of stochastic sequences with a finite time horizon $T$ known to the learner. The question we investigate is whether it is possible to derive vanishing regret bounds that hold with high probability, complementing existing bounds from the literature that hold in expectation. We propose such high-probability bounds which have a very similar form as the prior expectation bounds. For the case of universal prediction of a stochastic process over a countable alphabet, our bound states a convergence rate of $\mathcal{O}(T^{-1/2} δ^{-1/2})$ with probability as least $1-δ$ compared to prior known in-expectation bounds of the order $\mathcal{O}(T^{-1/2})$. We also propose an impossibility result which proves that it is not possible to improve the exponent of $δ$ in a bound of the same form without making additional assumptions.

Block-Sample MAC-Bayes Generalization Bounds

We present a family of novel block-sample MAC-Bayes bounds (mean approximately correct). While PAC-Bayes bounds (probably approximately correct) typically give bounds for the generalization error that hold with high probability, MAC-Bayes bounds have a similar form but bound the expected generalization error instead. The family of bounds we propose can be understood as a generalization of an expectation version of known PAC-Bayes bounds. Compared to standard PAC-Bayes bounds, the new bounds contain divergence terms that only depend on subsets (or \emph{blocks}) of the training data. The proposed MAC-Bayes bounds hold the promise of significantly improving upon the tightness of traditional PAC-Bayes and MAC-Bayes bounds. This is illustrated with a simple numerical example in which the original PAC-Bayes bound is vacuous regardless of the choice of prior, while the proposed family of bounds are finite for appropriate choices of the block size. We also explore the question whether high-probability versions of our MAC-Bayes bounds (i.e., PAC-Bayes bounds of a similar form) are possible. We answer this question in the negative with an example that shows that in general, it is not possible to establish a PAC-Bayes bound which (a) vanishes with a rate faster than $\mathcal{O}(1/\log n)$ whenever the proposed MAC-Bayes bound vanishes with rate $\mathcal{O}(n^{-1/2})$ and (b) exhibits a logarithmic dependence on the permitted error probability.

Low-Rank-Based Approximate Computation with Memristors

Memristor crossbars enable vector-matrix multiplication (VMM), and are promising for low-power applications. However, it can be difficult to write the memristor conductance values exactly. To improve the accuracy of VMM, we propose a scheme based on low-rank matrix approximation. Specifically, singular value decomposition (SVD) is first applied to obtain a low-rank approximation of the target matrix, which is then factored into a pair of smaller matrices. Subsequently, a two-step serial VMM is executed, where the stochastic write errors are mitigated through step-wise averaging. To evaluate the performance of the proposed scheme, we derive a general expression for the resulting computation error and provide an asymptotic analysis under a prescribed singular-value profile, which reveals how the error scales with matrix size and rank. Both analytical and numerical results confirm the superiority of the proposed scheme compared with the benchmark scheme.

RIS-assisted Physical Layer Security

We propose a reconfigurable intelligent surface (RIS)-assisted wiretap channel, where the RIS is strategically deployed to provide a spatial separation to the transmitter, and orthogonal combiners are employed at the legitimate receiver to extract the data streams from the direct and RIS-assisted links. Then we derive the achievable secrecy rate under semantic security for the RIS-assisted channel and design an algorithm for the secrecy rate optimization problem. The simulation results show the effects of total transmit power, the location and number of eavesdroppers on the security performance.

An Age of Information Characterization of SPS for V2X Applications

We derive a closed-form approximation of the stationary distribution of the Age of Information (AoI) of the semi-persistent scheduling (SPS) protocol which is a core part of NR-V2X, an important standard for vehicular communications. While prior works have studied the average AoI under similar assumptions, in this work we provide a full statistical characterization of the AoI by deriving an approximation of its probability mass function. As result, besides the average AoI, we are able to evaluate the age-violation probability, which is of particular relevance for safety-critical applications in vehicular domains, where the priority is to ensure that the AoI does not exceed a predefined threshold during system operation. The study reveals complementary behavior of the age-violation probability compared to the average AoI and highlights the role of the duration of the reservation as a key parameter in the SPS protocol. We use this to demonstrate how this crucial parameter should be tuned according to the performance requirements of the application.

Inverse Solvability and Security with Applications to Federated Learning

We introduce the concepts of inverse solvability and security for a generic linear forward model and demonstrate how they can be applied to models used in federated learning. We provide examples of such models which differ in the resulting inverse solvability and security as defined in this paper. We also show how the large number of users participating in a given iteration of federated learning can be leveraged to increase both solvability and security. Finally, we discuss possible extensions of the presented concepts including the nonlinear case.

A Learning-Based Approach to Approximate Coded Computation

Lagrange coded computation (LCC) is essential to solving problems about matrix polynomials in a coded distributed fashion; nevertheless, it can only solve the problems that are representable as matrix polynomials. In this paper, we propose AICC, an AI-aided learning approach that is inspired by LCC but also uses deep neural networks (DNNs). It is appropriate for coded computation of more general functions. Numerical simulations demonstrate the suitability of the proposed approach for the coded computation of different matrix functions that are often utilized in digital signal processing.