arXiv subjects

Houssem Sifaou

Publications and source records attributed to Houssem Sifaou.

At least 19 recordsLinked to original sources

arXiv2026

Event-triggered Implicit Perturbation for Zeroth-Order Fine-Tuning of Spiking Transformers

Zeroth-order (ZO) optimization estimates gradients using only forward-pass evaluations, making it suitable for fine-tuning non-differentiable, event-driven spiking neural networks (SNNs). However, its deployment on in-memory computing (IMC) accelerators is constrained by the repeated read-modify-write (RMW) operations arising from explicit weight perturbation and the prohibitive hardware footprint of random number generators (RNGs) for statistically independent per-weight perturbations. To address these challenges, we propose an implicit-perturbation ZO (IPZO) architecture in which perturbation sums computed by an event-triggered perturbation generation unit (PGU) are combined with the weighted sums produced by the IMC array, eliminating perturbation-induced RMW operations while preserving weight-stationary execution of IMC. By exploiting spike sparsity, the PGU generates and accumulates perturbation contributions only for spike-activated weight rows, reducing the required row dimension of the RNG array. An address-driven XOR recombination scheme (PGU-XOR) is further introduced to mitigate the spatial correlations caused by direct RNG reuse (PGU-Reuse). The results show that (1) PGU-XOR matches software RNGs in accuracy on Spikingformer/CIFAR-10 (76.41% vs. 76.53%) and perplexity (PPL) on SpikeGPT/WikiText-2 (54.20 vs. 53.23), whereas PGU-Reuse degrades accuracy by 9.56 percentage points and increases PPL by 11.8; (2) implemented in a TSMC 16-nm CMOS technology, PGU-XOR incurs 40.3%-46.0% area and 15.2%-48.9% energy overhead per matrix-vector multiplication relative to PGU-Reuse, yet its faster convergence reduces the total perturbation energy to 0.51x that of PGU-Reuse at iso-accuracy; (3) IPZO reduces the perturbation energy to 0.46x-0.83x that of conventional explicit weight perturbation for a batch size of B=64 and T=4 time steps, with the advantage growing as BT decreases.

cs.AR↗

arXiv2026

Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects

Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is identifying formulations capable of uncovering the common information shared between different but related tasks. This paper provides a precise asymptotic analysis of a popular multi--task formulation associated with misspecified perceptron learning models. The main contribution of this paper is to precisely determine the reasons behind the benefits gained from combining multiple related tasks. Specifically, we show that combining multiple tasks is asymptotically equivalent to a traditional formulation with additional regularization terms that help improve the generalization performance. Another contribution is to empirically study the impact of combining tasks on the generalization error. In particular, we empirically show that the combination of multiple tasks postpones the double descent phenomenon and can mitigate it asymptotically.

cs.LG↗

arXiv2025

On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization

On-device fine-tuning is a critical capability for edge AI systems, which must support adaptation to different agentic tasks under stringent memory constraints. Conventional backpropagation (BP)-based training requires storing layer activations and optimizer states, a demand that can be only partially alleviated through checkpointing. In edge deployments in which the model weights must reside entirely in device memory, this overhead severely limits the maximum model size that can be deployed. Memory-efficient zeroth-order optimization (MeZO) alleviates this bottleneck by estimating gradients using forward evaluations alone, eliminating the need for storing intermediate activations or optimizer states. This enables significantly larger models to fit within on-chip memory, albeit at the cost of potentially longer fine-tuning wall-clock time. This paper first provides a theoretical estimate of the relative model sizes that can be accommodated under BP and MeZO training. We then numerically validate the analysis, demonstrating that MeZO exhibits accuracy advantages under on-device memory constraints, provided sufficient wall-clock time is available for fine-tuning.

cs.LG↗

arXiv2025

Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization

Optimizing a reinforcement learning (RL) policy typically requires extensive interactions with a high-fidelity simulator of the environment, which are often costly or impractical. Offline RL addresses this problem by allowing training from pre-collected data, but its effectiveness is strongly constrained by the size and quality of the dataset. Hybrid offline-online RL leverages both offline data and interactions with a single simulator of the environment. In many real-world scenarios, however, multiple simulators with varying levels of fidelity and computational cost are available. In this work, we study multi-fidelity hybrid RL for policy optimization under a fixed cost budget. We introduce multi-fidelity hybrid RL via information gain maximization (MF-HRL-IGM), a hybrid offline-online RL algorithm that implements fidelity selection based on information gain maximization through a bootstrapping approach. Theoretical analysis establishes the no-regret property of MF-HRL-IGM, while empirical evaluations demonstrate its superior performance compared to existing benchmarks.

cs.LG↗

arXiv2025

Reliable Wireless Indoor Localization via Cross-Validated Prediction-Powered Calibration

Wireless indoor localization using predictive models with received signal strength information (RSSI) requires proper calibration for reliable position estimates. One remedy is to employ synthetic labels produced by a (generally different) predictive model. But fine-tuning an additional predictor, as well as estimating residual bias of the synthetic labels, demands additional data, aggravating calibration data scarcity in wireless environments. This letter proposes an approach that efficiently uses limited calibration data to simultaneously fine-tune a predictor and estimate the bias of synthetic labels, yielding prediction sets with rigorous coverage guarantees. Experiments on a fingerprinting dataset validate the effectiveness of the proposed method.

cs.LG↗

arXiv2025

How to Bridge the Sim-to-Real Gap in Digital Twin-Aided Telecommunication Networks

Training effective artificial intelligence models for telecommunications is challenging due to the scarcity of deployment-specific data. Real data collection is expensive, and available datasets often fail to capture the unique operational conditions and contextual variability of the network environment. Digital twinning provides a potential solution to this problem, as simulators tailored to the current network deployment can generate site-specific data to augment the available training datasets. However, there is a need to develop solutions to bridge the inherent simulation-to-reality (sim-to-real) gap between synthetic and real-world data. This paper reviews recent advances on two complementary strategies: 1) the calibration of digital twins (DTs) through real-world measurements, and 2) the use of sim-to-real gap-aware training strategies to robustly handle residual discrepancies between digital twin-generated and real data. For the latter, we evaluate two conceptually distinct methods that model the sim-to-real gap either at the level of the environment via Bayesian learning or at the level of the training loss via prediction-powered inference.

eess.SP↗

arXiv2025

Context-Aware Doubly-Robust Semi-Supervised Learning

The widespread adoption of artificial intelligence (AI) in next-generation communication systems is challenged by the heterogeneity of traffic and network conditions, which call for the use of highly contextual, site-specific, data. A promising solution is to rely not only on real-world data, but also on synthetic pseudo-data generated by a network digital twin (NDT). However, the effectiveness of this approach hinges on the accuracy of the NDT, which can vary widely across different contexts. To address this problem, this paper introduces context-aware doubly-robust (CDR) learning, a novel semi-supervised scheme that adapts its reliance on the pseudo-data to the different levels of fidelity of the NDT across contexts. CDR is evaluated on the task of downlink beamforming where it outperforms previous state-of-the-art approaches, providing a 24% loss decrease when compared to doubly-robust (DR) semi-supervised learning in regimes with low labeled data availability.

eess.SP↗

arXiv2024

Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning

Reinforcement learning (RL) has been widely adopted for controlling and optimizing complex engineering systems such as next-generation wireless networks. An important challenge in adopting RL is the need for direct access to the physical environment. This limitation is particularly severe in multi-agent systems, for which conventional multi-agent reinforcement learning (MARL) requires a large number of coordinated online interactions with the environment during training. When only offline data is available, a direct application of online MARL schemes would generally fail due to the epistemic uncertainty entailed by the lack of exploration during training. In this work, we propose an offline MARL scheme that integrates distributional RL and conservative Q-learning to address the environment's inherent aleatoric uncertainty and the epistemic uncertainty arising from the use of offline data. We explore both independent and joint learning strategies. The proposed MARL scheme, referred to as multi-agent conservative quantile regression, addresses general risk-sensitive design criteria and is applied to the trajectory planning problem in drone networks, showcasing its advantages.

cs.LG↗

arXiv2024

Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems

In many wireless application scenarios, acquiring labeled data can be prohibitively costly, requiring complex optimization processes or measurement campaigns. Semi-supervised learning leverages unlabeled samples to augment the available dataset by assigning synthetic labels obtained via machine learning (ML)-based predictions. However, treating the synthetic labels as true labels may yield worse-performing models as compared to models trained using only labeled data. Inspired by the recently developed prediction-powered inference (PPI) framework, this work investigates how to leverage the synthetic labels produced by an ML model, while accounting for the inherent bias concerning true labels. To this end, we first review PPI and its recent extensions, namely tuned PPI and cross-prediction-powered inference (CPPI). Then, we introduce two novel variants of PPI. The first, referred to as tuned CPPI, provides CPPI with an additional degree of freedom in adapting to the quality of the ML-based labels. The second, meta-CPPI (MCPPI), extends tuned CPPI via the joint optimization of the ML labeling models and of the parameters of interest. Finally, we showcase two applications of PPI-based techniques in wireless systems, namely beam alignment based on channel knowledge maps in millimeter-wave systems and received signal strength information-based indoor localization. Simulation results show the advantages of PPI-based techniques over conventional approaches that rely solely on labeled data or that apply standard pseudo-labeling strategies from semi-supervised learning. Furthermore, the proposed tuned CPPI method is observed to guarantee the best performance among all benchmark schemes, especially in the regime of limited labeled data.

cs.IT↗

arXiv2023

Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMO

Cell-free massive MIMO is emerging as a promising technology for future wireless communication systems, which is expected to offer uniform coverage and high spectral efficiency compared to classical cellular systems. We study in this paper how cell-free massive MIMO can support federated edge learning. Taking advantage of the additive nature of the wireless multiple access channel, over-the-air computation is exploited, where the clients send their local updates simultaneously over the same communication resource. This approach, known as over-the-air federated learning (OTA-FL), is proven to alleviate the communication overhead of federated learning over wireless networks. Considering channel correlation and only imperfect channel state information available at the central server, we propose a practical implementation of OTA-FL over cell-free massive MIMO. The convergence of the proposed implementation is studied analytically and experimentally, confirming the benefits of cell-free massive MIMO for OTA-FL.

eess.SP↗

arXiv2022

CSI-fingerprinting Indoor Localization via Attention-Augmented Residual Convolutional Neural Network

Deep learning has been widely adopted for channel state information (CSI)-fingerprinting indoor localization systems. These systems usually consist of two main parts, i.e., a positioning network that learns the mapping from high-dimensional CSI to physical locations and a tracking system that utilizes historical CSI to reduce the positioning error. This paper presents a new localization system with high accuracy and generality. On the one hand, the receptive field of the existing convolutional neural network (CNN)-based positioning networks is limited, restricting their performance as useful information in CSI is not explored thoroughly. As a solution, we propose a novel attention-augmented residual CNN to utilize the local information and global context in CSI exhaustively. On the other hand, considering the generality of a tracking system, we decouple the tracking system from the CSI environments so that one tracking system for all environments becomes possible. Specifically, we remodel the tracking problem as a denoising task and solve it with deep trajectory prior. Furthermore, we investigate how the precision difference of inertial measurement units will adversely affect the tracking performance and adopt plug-and-play to solve the precision difference problem. Experiments show the superiority of our methods over existing approaches in performance and generality improvement.

eess.SP↗

arXiv2022

Robust Federated Learning via Over-The-Air Computation

This paper investigates the robustness of over-the-air federated learning to Byzantine attacks. The simple averaging of the model updates via over-the-air computation makes the learning task vulnerable to random or intended modifications of the local model updates of some malicious clients. We propose a robust transmission and aggregation framework to such attacks while preserving the benefits of over-the-air computation for federated learning. For the proposed robust federated learning, the participating clients are randomly divided into groups and a transmission time slot is allocated to each group. The parameter server aggregates the results of the different groups using a robust aggregation technique and conveys the result to the clients for another training round. We also analyze the convergence of the proposed algorithm. Numerical simulations confirm the robustness of the proposed approach to Byzantine attacks.

cs.LG↗

arXiv2022

Performance Analysis of Regularized Convex Relaxation for Complex-Valued Data Detection

In this work, we study complex-valued data detection performance in massive multiple-input multiple-output (MIMO) systems. We focus on the problem of recovering an $n$-dimensional signal whose entries are drawn from an arbitrary constellation $\mathcal{K} \subset \mathbb{C}$ from $m$ noisy linear measurements, with an independent and identically distributed (i.i.d.) complex Gaussian channel. Since the optimal maximum likelihood (ML) detector is computationally prohibitive for large dimensions, many convex relaxation heuristic methods have been proposed to solve the detection problem. In this paper, we consider a regularized version of this convex relaxation that we call the regularized convex relaxation (RCR) detector and sharply derive asymptotic expressions for its mean square error and symbol error probability. Monte-Carlo simulations are provided to validate the derived analytical results.

cs.IT↗

arXiv2022

Over-The-Air Federated Learning under Byzantine Attacks

Federated learning (FL) is a promising solution to enable many AI applications, where sensitive datasets from distributed clients are needed for collaboratively training a global model. FL allows the clients to participate in the training phase, governed by a central server, without sharing their local data. One of the main challenges of FL is the communication overhead, where the model updates of the participating clients are sent to the central server at each global training round. Over-the-air computation (AirComp) has been recently proposed to alleviate the communication bottleneck where the model updates are sent simultaneously over the multiple-access channel. However, simple averaging of the model updates via AirComp makes the learning process vulnerable to random or intended modifications of the local model updates of some Byzantine clients. In this paper, we propose a transmission and aggregation framework to reduce the effect of such attacks while preserving the benefits of AirComp for FL. For the proposed robust approach, the central server divides the participating clients randomly into groups and allocates a transmission time slot for each group. The updates of the different groups are then aggregated using a robust aggregation technique. We extend our approach to handle the case of non-i.i.d. local data, where a resampling step is added before robust aggregation. We analyze the convergence of the proposed approach for both cases of i.i.d. and non-i.i.d. data and demonstrate that the proposed algorithm converges at a linear rate to a neighborhood of the optimal solution. Experiments on real datasets are provided to confirm the robustness of the proposed approach.

cs.LG↗

arXiv2021

A Precise Performance Analysis of Support Vector Regression

In this paper, we study the hard and soft support vector regression techniques applied to a set of $n$ linear measurements of the form $y_i=\boldsymbolβ_\star^{T}{\bf x}_i +n_i$ where $\boldsymbolβ_\star$ is an unknown vector, $\left\{{\bf x}_i\right\}_{i=1}^n$ are the feature vectors and $\left\{{n}_i\right\}_{i=1}^n$ model the noise. Particularly, under some plausible assumptions on the statistical distribution of the data, we characterize the feasibility condition for the hard support vector regression in the regime of high dimensions and, when feasible, derive an asymptotic approximation for its risk. Similarly, we study the test risk for the soft support vector regression as a function of its parameters. Our results are then used to optimally tune the parameters intervening in the design of hard and soft support vector regression algorithms. Based on our analysis, we illustrate that adding more samples may be harmful to the test performance of support vector regression, while it is always beneficial when the parameters are optimally selected. Such a result reminds a similar phenomenon observed in modern learning architectures according to which optimally tuned architectures present a decreasing test performance curve with respect to the number of samples.

cs.LG↗

arXiv2020

Precise Error Analysis of the LASSO under Correlated Designs

In this paper, we consider the problem of recovering a sparse signal from noisy linear measurements using the so called LASSO formulation. We assume a correlated Gaussian design matrix with additive Gaussian noise. We precisely analyze the high dimensional asymptotic performance of the LASSO under correlated design matrices using the Convex Gaussian Min-max Theorem (CGMT). We define appropriate performance measures such as the mean-square error (MSE), probability of support recovery, element error rate (EER) and cosine similarity. Numerical simulations are presented to validate the derived theoretical results.

math.ST↗

arXiv2020

High-Dimensional Quadratic Discriminant Analysis under Spiked Covariance Model

Quadratic discriminant analysis (QDA) is a widely used classification technique that generalizes the linear discriminant analysis (LDA) classifier to the case of distinct covariance matrices among classes. For the QDA classifier to yield high classification performance, an accurate estimation of the covariance matrices is required. Such a task becomes all the more challenging in high dimensional settings, wherein the number of observations is comparable with the feature dimension. A popular way to enhance the performance of QDA classifier under these circumstances is to regularize the covariance matrix, giving the name regularized QDA (R-QDA) to the corresponding classifier. In this work, we consider the case in which the population covariance matrix has a spiked covariance structure, a model that is often assumed in several applications. Building on the classical QDA, we propose a novel quadratic classification technique, the parameters of which are chosen such that the fisher-discriminant ratio is maximized. Numerical simulations show that the proposed classifier not only outperforms the classical R-QDA for both synthetic and real data but also requires lower computational complexity, making it suitable to high dimensional settings.

cs.LG↗

arXiv2017

Optimal Linear Precoding for Indoor Visible Light Communication System

Visible light communication (VLC) is an emerging technique that uses light-emitting diodes (LED) to combine communication and illumination. It is considered as a promising scheme for indoor wireless communication that can be deployed at reduced costs while offering high data rate performance. In this paper, we focus on the design of the downlink of a multi-user VLC system. Inherent to multi-user systems is the interference caused by the broadcast nature of the medium. Linear precoding based schemes are among the most popular solutions that have recently been proposed to mitigate inter-user interference. This paper focuses on the design of the optimal linear precoding scheme that solves the max-min signal-to-interference-plus-noise ratio (SINR) problem. The performance of the proposed precoding scheme is studied under different working conditions and compared with the classical zero-forcing precoding. Simulations have been provided to illustrate the high gain of the proposed scheme.

eess.SP↗