In this paper, a novel channel modeling approach, named light detection and ranging (LiDAR)-aided geometry-based stochastic modeling (LA-GBSM), is developed. Based on the developed LA-GBSM approach, a new millimeter wave (mmWave) channel model for sixth-generation (6G) vehicular intelligent sensing-communication integration is proposed, which can support the design of intelligent transportation systems (ITSs). The proposed LA-GBSM is accurately parameterized under high, medium, and low vehicular traffic density (VTD) conditions via a sensing-communication simulation dataset with LiDAR point clouds and scatterer information for the first time. Specifically, by detecting dynamic vehicles and static building/tress through LiDAR point clouds via machine learning, scatterers are divided into static and dynamic scatterers. Furthermore, statistical distributions of parameters, e.g., distance, angle, number, and power, related to static and dynamic scatterers are quantified under high, medium, and low VTD conditions. To mimic channel non-stationarity and consistency, based on the quantified statistical distributions, a new visibility region (VR)-based algorithm in consideration of newly generated static/dynamic scatterers is developed. Key channel statistics are derived and simulated. By comparing simulation results and ray-tracing (RT)-based results, the utility of the proposed LA-GBSM is verified.
Integrated sensing and communications (ISAC) is a critical enabler for emerging 6G applications, and at its core lies in the dual-functional waveform design. While orthogonal frequency division multiplexing (OFDM) has been a popular basic waveform, its primitive version falls short in sensing due to the inherent unregulated auto-correlation properties. Furthermore, the sensitivity to Doppler shift hinders its broader applications in dynamic scenarios. To address these issues, we propose a superposed index-modulated OFDM (S-IM-OFDM). The proposed scheme improves the sensing performance without excess power consumption by translating the energy efficiency of IM-OFDM onto sensing-oriented signals over OFDM. Also, it maintains excellent communication performance in time-varying channels by leveraging the sensed parameters to compensate for Doppler. Compared to conventional OFDM, the proposed S-IM-OFDM waveform exhibits better sensing capabilities and wider applicability in dynamic scenarios. Both theoretical analyses and simulations corroborate its dual benefits.
Integrated Sensing and Communication (ISAC) emerges as a promising technology for B5G/6G, particularly in the millimeter-wave (mmWave) band. However, the widespread adoption of hybrid architecture in mmWave systems compromises multiplexing gain due to limited radio-frequency chains, resulting in mediocre performance when embedding sensing functionality. To avoid sacrificing the spectrum efficiency in hybrid structures while addressing performance bottlenecks in its extension to ISAC, we present an optimized beam pattern modulation-embedded ISAC (BPM-ISAC). BPM-ISAC applies index modulation over beamspace by selectively activating communication beams, aiming to minimize sensing beampattern mean squared error (MSE) under communication MSE constraints through dedicated hybrid transceiver design. Optimization involves the analog part through a min-MSE-based beam selection algorithm, followed by the digital part using an alternating optimization algorithm. Convergence and asymptotic pairwise error probability (APEP) analyses accompany numerical simulations, validating its overall enhanced ISAC performance over existing alternatives.
The development of Intelligent Transportation System (ITS) has brought about comprehensive urban traffic information that not only provides convenience to urban residents in their daily lives but also enhances the efficiency of urban road usage, leading to a more harmonious and sustainable urban life. Typical scenarios in ITS mainly include traffic flow prediction, traffic target recognition, and vehicular edge computing. However, most current ITS applications rely on a centralized training approach where users upload source data to a cloud server with high computing power for management and centralized training. This approach has limitations such as poor real-time performance, data silos, and difficulty in guaranteeing data privacy. To address these limitations, federated learning (FL) has been proposed as a promising solution. In this paper, we present a comprehensive review of the application of FL in ITS, with a particular focus on three key scenarios: traffic flow prediction, traffic target recognition, and vehicular edge computing. For each scenario, we provide an in-depth analysis of its key characteristics, current challenges, and specific manners in which FL is leveraged. Moreover, we discuss the benefits that FL can offer as a potential solution to the limitations of the centralized training approach currently used in ITS applications.
We study the task of efficiently sampling from a Gibbs distribution $d \pi^* = e^{-h} d {vol}_g$ over a Riemannian manifold $M$ via (geometric) Langevin MCMC; this algorithm involves computing exponential maps in random Gaussian directions and is efficiently implementable in practice. The key to our analysis of Langevin MCMC is a bound on the discretization error of the geometric Euler-Murayama scheme, assuming $\nabla h$ is Lipschitz and $M$ has bounded sectional curvature. Our error bound matches the error of Euclidean Euler-Murayama in terms of its stepsize dependence. Combined with a contraction guarantee for the geometric Langevin Diffusion under Kendall-Cranston coupling, we prove that the Langevin MCMC iterates lie within $\epsilon$-Wasserstein distance of $\pi^*$ after $\tilde{O}(\epsilon^{-2})$ steps, which matches the iteration complexity for Euclidean Langevin MCMC. Our results apply in general settings where $h$ can be nonconvex and $M$ can have negative Ricci curvature. Under additional assumptions that the Riemannian curvature tensor has bounded derivatives, and that $\pi^*$ satisfies a $CD(\cdot,\infty)$ condition, we analyze the stochastic gradient version of Langevin MCMC, and bound its iteration complexity by $\tilde{O}(\epsilon^{-2})$ as well.
Many neural network architectures have been shown to be Turing Complete, and can thus implement arbitrary algorithms. However, Transformers are unique in that they can implement gradient-based learning algorithms \emph{under simple parameter configurations}. A line of recent work shows that linear Transformers naturally learn to implement gradient descent (GD) when trained on a linear regression in-context learning task. But the linearity assumption (either in the Transformer architecture or in the learning task) is far from realistic settings where non-linear activations crucially enable Transformers to learn complicated non-linear functions. In this paper, we provide theoretical and empirical evidence that non-linear Transformers can, and \emph{in fact do}, learn to implement learning algorithms to learn non-linear functions in context. Our results apply to a broad class of combinations of non-linear architectures, and non-linear in-context learning tasks. Interestingly, we show that the optimal choice of non-linear activation depends in a natural way on the non-linearity of the learning task.
This paper proposes a novel three-dimensional (3D) theoretical regular-shaped geometry-based stochastic model (RS-GBSM) and the corresponding sum-of-sinusoids (SoS) simulation model for non-isotropic multiple-input multiple-output (MIMO) vehicle-to-vehicle (V2V) Ricean fading channels. The proposed RS-GBSM, combining line-of-sight (LoS) components, a two-sphere model, and an elliptic-cylinder model, has the ability to study the impact of the vehicular traffic density (VTD) on channel statistics, and jointly considers the azimuth and elevation angles by using the von Mises Fisher distribution. Moreover, a novel parameter computation method is proposed for jointly calculating the azimuth and elevation angles in the SoS channel simulator. Based on the proposed 3D theoretical RS-GBSM and its SoS simulation model, statistical properties are derived and thoroughly investigated. The impact of the elevation angle in the 3D model on key statistical properties is investigated by comparing with those of the corresponding two-dimensional (2D) model. It is demonstrated that the 3D model is more accurate to characterize real V2V channels, in particular for pico cell scenarios. Finally, close agreement is achieved between the theoretical model, SoS simulation model, and simulation results, demonstrating the utility of the proposed models.
The future of vehicular communication networks relies on mmWave massive multi-input-multi-output antenna arrays for intensive data transfer and massive vehicle access. However, reliable vehicle-to-infrastructure links require narrow beam alignment, which traditionally involves excessive signaling overhead. To address this issue, we propose a novel proactive beamforming scheme that integrates multi-modal sensing and communications via Multi-Modal Feature Fusion Network (MMFF-Net), which is composed of multiple neural network components with distinct functions. Unlike existing methods that rely solely on communication processing, our approach obtains comprehensive environmental features to improve beam alignment accuracy. We verify our scheme on the ViWi dataset, which we enriched with realistic vehicle drifting behavior. Our proposed MMFF-Net achieves more accurate and stable angle prediction, which in turn increases the achievable rates and reduces the communication system outage probability. Even in complex dynamic scenarios, robust prediction results can be guaranteed, demonstrating the feasibility and practicality of the proposed proactive beamforming approach.
Transformer training is notoriously difficult, requiring a careful design of optimizers and use of various heuristics. We make progress towards understanding the subtleties of training transformers by carefully studying a simple yet canonical linearized shallow transformer model. Specifically, we train linear transformers to solve regression tasks, inspired by J. von Oswald et al. (ICML 2023), and K. Ahn et al. (NeurIPS 2023). Most importantly, we observe that our proposed linearized models can reproduce several prominent aspects of transformer training dynamics. Consequently, the results obtained in this paper suggest that a simple linearized transformer model could actually be a valuable, realistic abstraction for understanding transformer optimization.