Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers

We investigate cluster formation, involving the number and composition of clusters, in decentralized federated learning (FL) with heterogeneous machine learning (ML) optimizers. While clustering in centralized FL has enabled scalability and resource savings, its value and development in fully decentralized environments have yet to be explored. Optimizing cluster formation in such environments is challenging, especially due to the complex coupling between network graph structures, local data heterogeneity, and different local ML model optimizers. To address these challenges, we propose serverless semi-decentralized FL (SSD-FL), a methodology requiring no persistent server infrastructure. In SSD-FL, cluster formation occurs via a lightweight, one-time device-to-device (D2D) initialization phase, after which actual ML model training (alongside consensus and convergence processes) is fully serverless. Functionally, SSD-FL segments global rounds into intra-cluster and inter-cluster regimes, ensuring global convergence and consensus through novel "effective loss functions" that integrate device-specific ML optimizers with network graph-based regularization. Next, SSD-FL leverages the consensus gap via the Cheeger inequality to develop an iterative clustering algorithm evaluated against our derived convergence and consensus bounds, which incorporate a unique scoring metric to quantify data and optimizer heterogeneity across devices. Finally, experimental evaluation against three categories of decentralized FL methodologies validate that SSD-FL improves both convergence speeds and communication efficiency across various network graphs, datasets, and local optimizer regimes.

Adversarial Water-Filling: Theory, Algorithms and Foundation Model

Competitive resource allocation problems over frequency and space can be formulated as minimax interaction between transmit power and worst-case interference. This formulation naturally arises in multi-operator low Earth orbit (LEO) satellite spectrum sharing, where transmissions from competing constellations interfere in real-time. Under Gaussian channels, AWF is strongly convex--concave on nondegenerate active channels, whereas discrete constellations yield generally nonconvex mercury/water-filling formulations. In this paper we propose the Adversarial Water-Filling (AWF) problem with corresponding theory and algorithms for these real situations. In addition, we develop a wireless foundation model for AWF to learn the AWF search dynamics. The architecture incorporates permutation-invariant channel representations, a constraint-aware graph neural network (GNN) with sparse message passing, and global latent variables capturing the low-dimensional water level implied by the AWF optimality. Through learned projected extragradient iterations, the model approximates stationary solutions of the constrained minimax problem arising under mercury/water-filling. We further show that, under local regularity and contractivity conditions, the learned AWF dynamics converge locally linearly around regular stationary points. Experiments demonstrate empirical generalization across unseen problem sizes, different constraints, and multiple discrete constellations, while achieving more than one-order-of-magnitude runtime improvements over iterative baselines. The related code can be found at https://github.com/convexsoft/AWF.

Optimizing Server Placement for Vertical Federated Learning in Dynamic Edge/Fog Networks

We investigate the control and optimization of vertical federated learning (VFL), a class of distributed machine learning (ML) methods in which edge/fog devices contain separate data features, in dynamic edge/fog networks. Owing to heterogeneous data features and hardware across edge/fog networks, devices' contributions to VFL vary substantially, and, moreover, dynamic edge/fog networks can lead to the permanent exit or entry of select data features. In this setting, our proposed methodology, server controlled VFL in dynamic networks (SC-DN), first establishes the existence of a global first-order stationary point for every global round, and then leverages this result to jointly optimize ML model training and resource consumption based on four key control variables: (i) server placement, (ii) device-to-server transmit power, (iii) local device processor frequency, and (iv) local training iterations per global round. The resulting optimization formulation contains coupled variables as well as numerous forms of logarithmic constraints which we show is a mixed-integer signomial program, an NP-hard problem, and for which we develop a general solver. Finally, via experiments on both image and multi-modal datasets, we show that our methodology demonstrates superior classification/regression performance and resource consumption savings than even greedy methodologies.

Covariance-Aware Demapping on Fourier-Curve Constellations

Injecting artificial noise (AN) along the tangent space of a curved constellation makes each transmitted symbol induce a Gaussian observation with a symbol-dependent rank-one covariance, so the matched maximum-likelihood (ML) decoder differs from the Euclidean nearest-neighbor decoder by a single rank-one correction per candidate. We develop a baseband-demapper realization of this correction for the Fourier-curve constellation and instantiate a regular $(3,6)$ low-density parity-check (LDPC)-coded link at $(k,M){=}(20,64)$. Against four baselines (Euclidean-mismatched, flat-constellation isotropic-AN, no-AN, and same-spectral-efficiency narrowband), the matched decoder extends the BLER${=}10^{-1}$ operating range by approximately $5$\,dB over the Euclidean-mismatched counterpart on the same tangent-AN transmitter, at a cost of $2kM$ additional multiply-accumulate operations per symbol ($+50\%/+100\%$ under residual/template-correlation accounting) and a $20$\,KB constellation--tangent lookup table ($10$\,KB incremental over a Euclidean template-only LUT). A bit-interleaved coded-modulation achievable-rate (BICM-AIR) computation supports the same matched-metric advantage at the tested labeling and max-log demapper, indicating that the BLER gain is not merely an artifact of this particular LDPC simulation, and a Woodbury extension generalizes the rank-one correction to per-tone Ricean fading. In the tested Monte-Carlo runs, a design-aware bounded-search eavesdropper without the phase-key shows no successful LDPC decoding at any tested $k\in\{2,8,20\}$ within a $B{=}10^{3}$ non-code-aided search budget; code-aided, multi-frame, and known-preamble attacks are left to follow-up work. LUT quantization down to $6$ bits yields no measurable coded-BLER degradation at the tested operating points.

Cooperative Multi-Satellite ISAC Networks: Centralized vs. Distributed Sensing

This paper investigates a downlink multi-satellite integrated sensing and communication (ISAC) network, in which multiple satellites simultaneously transmit ISAC signals to provide communication services to ground user equipments and enable cooperative sensing of airborne targets through multiple gateways. To support this dual functionality, we introduce communication and sensing beamforming designs based on uniform planar arrays with optimized power allocation. Building on these designs, we propose two cooperative sensing frameworks, namely centralized and distributed. In the centralized framework, each gateway forwards its sensing observations to a central unit (CU), where the positions of multiple targets are jointly estimated from the aggregated data using a sparse signal recovery formulation. To mitigate the signaling overhead inherent in centralized processing, a distributed framework is further proposed, in which each gateway independently estimates target positions and transmits only the local estimates to the CU. To associate estimates from different gateways, a data association problem based on the squared Euclidean distance is formulated and efficiently solved using the Hungarian algorithm. The final target positions are then obtained by minimizing the distance estimation error. Simulation results demonstrate that the proposed centralized and distributed frameworks significantly outperform existing sensing schemes while satisfying communication performance requirements. We also evaluate the sensing-communication trade-off from the viewpoints of sensing accuracy and communication power consumption under the proposed frameworks.

From Specialist to Large Models: A Paradigm Evolution Towards Semantic-Aware MIMO

The sixth generation (6G) network is expected to deploy larger multiple-input multiple-output (MIMO) arrays to support massive connectivity, which will increase overhead and latency at the physical layer. Meanwhile, emerging 6G demands such as immersive communications and environmental sensing pose challenges to traditional signal processing. To address these issues, we propose the ``semantic-aware MIMO'' paradigm, which leverages specialist models and large models to perceive, utilize, and fuse the inherent semantics of channels and sources for improved performance. Moreover, for representative MIMO physical-layer tasks, e.g., random access activity detection, channel feedback, and precoding, we design specialist models that exploit channel and source semantics for better performance. Additionally, in view of the more diversified functions of 6G MIMO, we further explore large models as a scalable solution for multi-task semantic-aware MIMO and review recent advances along with their advantages and limitations. Finally, we discuss the challenges, insights, and prospects of the evolution of specialist models and large models empowered semantic-aware MIMO paradigms.

Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control and Management

Open Radio Access Networks (O-RAN) promise flexible 6G network access through disaggregated, software-driven components and open interfaces, but this programmability also increases operational complexity. Multiple control loops coexist across the service management layer and RAN Intelligent Controller (RIC), while independently developed control applications can interact in unintended ways. In parallel, recent advances in generative Artificial Intelligence (AI) are enabling a shift from isolated AI models toward agentic AI systems that can interpret goals, coordinate multiple models and control functions, and adapt their behavior over time. This article proposes a multi-scale agentic AI framework for O-RAN that organizes RAN intelligence as a coordinated hierarchy across the Non-Real-Time (Non-RT), Near-Real-Time (Near-RT), and Real-Time (RT) control loops: (i) A Large Language Model (LLM) agent in the Non-RT RIC translates operator intent into policies and governs model lifecycles. (ii) Small Language Model (SLM) agents in the Near-RT RIC execute low-latency optimization and can activate, tune, or disable existing control applications; and (iii) Wireless Physical-layer Foundation Model (WPFM) agents near the distributed unit provide fast inference close to the air interface. We describe how these agents cooperate through standardized O-RAN interfaces and telemetry. Using a proof-of-concept implementation built on open-source models, software, and datasets, we demonstrate the proposed agentic approach in two representative scenarios: robust operation under non-stationary conditions and intent-driven slice resource control.

Quantization-Aware Collaborative Inference for Large Embodied AI Models

Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computational demands of LAIMs pose significant challenges for resource-limited embodied agents. To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems. First, we develop a tractable approximation for quantization-induced inference distortion. Based on this approximation, we derive lower and upper bounds on the quantization rate-inference distortion function, characterizing its dependence on LAIM statistics, including the quantization bit-width. Next, we formulate a joint quantization bit-width and computation frequency design problem under delay and energy constraints, aiming to minimize the distortion upper bound while ensuring tightness through the corresponding lower bound. Extensive evaluations validate the proposed distortion approximation, the derived rate-distortion bounds, and the effectiveness of the proposed joint design. Particularly, simulations and real-world testbed experiments demonstrate the effectiveness of the proposed joint design in balancing inference quality, latency, and energy consumption in edge embodied AI systems.

An Elementary Approach to Scheduling in Generative Diffusion Models

An elementary approach to characterizing the impact of noise scheduling and time discretization in generative diffusion models is developed. Considering a simplified model where the source distribution is multivariate Gaussian with a given covariance matrix, the explicit closed-form evolution trajectory of the distributions across reverse sampling steps is derived, and consequently, the Kullback-Leibler (KL) divergence between the source distribution and the reverse sampling output is obtained. The effect of the number of time discretization steps on the convergence of this KL divergence is studied via the Euler-Maclaurin expansion. An optimization problem is formulated, and its solution noise schedule is obtained via calculus of variations, shown to follow a tangent law whose coefficient is determined by the eigenvalues of the source covariance matrix. For an alternative scenario, more realistic in practice, where pretrained models have been obtained for some given noise schedules, the KL divergence also provides a measure to compare different time discretization strategies in reverse sampling. Experiments across different datasets and pretrained models demonstrate that the time discretization strategy selected by our approach consistently outperforms baseline and search-based strategies, particularly when the budget on the number of function evaluations is very tight.

Empirical Risk Minimization with $f$-Divergence Regularization

In this paper, the solution to the empirical risk minimization problem with $f$-divergence regularization (ERM-$f$DR) is presented and conditions under which the solution also serves as the solution to the minimization of the expected empirical risk subject to an $f$-divergence constraint are established. The proposed approach extends applicability to a broader class of $f$-divergences than previously reported and yields theoretical results that recover previously known results. Additionally, the difference between the expected empirical risk of the ERM-$f$DR solution and that of its reference measure is characterized, providing insights into previously studied cases of $f$-divergences. A central contribution is the introduction of the normalization function, a mathematical object that is critical in both the dual formulation and practical computation of the ERM-$f$DR solution. This work presents an implicit characterization of the normalization function as a nonlinear ordinary differential equation (ODE), establishes its key properties, and subsequently leverages them to construct a numerical algorithm for approximating the normalization factor under mild assumptions. Further analysis demonstrates structural equivalences between ERM-$f$DR problems with different $f$-divergences via transformations of the empirical risk. Finally, the proposed algorithm is used to compute the training and test risks of ERM-$f$DR solutions under different $f$-divergence regularizers. This numerical example highlights the practical implications of choosing different functions $f$ in ERM-$f$DR problems.