Nicolò Michelusi

Frank Po-Chen Lin, Seyyedali Hosseinalipour, Nicolò Michelusi et al.

Federated learning has gained popularity as a means of training models distributed across the wireless edge. The paper introduces delay-aware hierarchical federated learning (DFL) to improve the efficiency of distributed machine learning (ML) model training by accounting for communication delays between edge and cloud. Different from traditional federated learning, DFL leverages multiple stochastic gradient descent iterations on local datasets within each global aggregation period and intermittently aggregates model parameters through edge servers in local subnetworks. During global synchronization, the cloud server consolidates local models with the outdated global model using a local-global combiner, thus preserving crucial elements of both, enhancing learning efficiency under the presence of delay. A set of conditions is obtained to achieve the sub-linear convergence rate of O(1/k) for strongly convex and smooth loss functions. Based on these findings, an adaptive control algorithm is developed for DFL, implementing policies to mitigate energy consumption and communication latency while aiming for sublinear convergence. Numerical evaluations show DFL's superior performance in terms of faster global model convergence, reduced resource consumption, and robustness against communication delays compared to existing FL algorithms. In summary, this proposed method offers improved efficiency and results when dealing with both convex and non-convex loss functions.

Nicolo' Michelusi

Implementing Decentralized Gradient Descent (DGD) in wireless systems is challenging due to noise, fading, and limited bandwidth, necessitating topology awareness, transmission scheduling, and the acquisition of channel state information (CSI) to mitigate interference and maintain reliable communications. These operations may result in substantial signaling overhead and scalability challenges in large networks lacking central coordination. This paper introduces a scalable DGD algorithm that eliminates the need for scheduling, topology information, or CSI (both average and instantaneous). At its core is a Non-Coherent Over-The-Air (NCOTA) consensus scheme that exploits a noisy energy superposition property of wireless channels. Nodes encode their local optimization signals into energy levels within an OFDM frame and transmit simultaneously, without coordination. The key insight is that the received energy equals, on average, the sum of the energies of the transmitted signals, scaled by their respective average channel gains, akin to a consensus step. This property enables unbiased consensus estimation, utilizing average channel gains as mixing weights, thereby removing the need for their explicit design or for CSI. Introducing a consensus stepsize mitigates consensus estimation errors due to energy fluctuations around their expected values. For strongly-convex problems, it is shown that the expected squared distance between the local and globally optimum models vanishes at a rate of O(1/sqrt{k}) after k iterations, with suitable decreasing learning and consensus stepsizes. Extensions accommodate a broad class of fading models and frequency-selective channels. Numerical experiments on image classification demonstrate faster convergence in terms of running time compared to state-of-the-art schemes, especially in dense network scenarios.

Bharath Keshavamurthy, Nicolo Michelusi

We describe the orchestration of a decentralized swarm of rotary-wing UAV-relays, augmenting the coverage and service capabilities of a terrestrial base station. Our goal is to minimize the time-average service latencies involved in handling transmission requests from ground users under Poisson arrivals, subject to an average UAV power constraint. Equipped with rate adaptation to efficiently leverage air-to-ground channel stochastics, we first derive the optimal control policy for a single relay via a semi-Markov decision process formulation, with competitive swarm optimization for UAV trajectory design. Accordingly, we detail a multiscale decomposition of this construction: outer decisions on radial wait velocities and end positions optimize the expected long-term delay-power trade-off; consequently, inner decisions on angular wait velocities, service schedules, and UAV trajectories greedily minimize the instantaneous delay-power costs. Next, generalizing to UAV swarms via replication and consensus-driven command-and-control, this policy is embedded with spread maximization and conflict resolution heuristics. We demonstrate that our framework offers superior performance with respect to average service latencies and average per-UAV power consumption: 11x faster data payload delivery relative to static UAV-relay deployments and 2x faster than a deep-Q network solution; remarkably, one relay with our scheme outclasses three relays under a joint successive convex approximation policy by 62%.

Muhammad Faraz Ul Abrar, Nicolò Michelusi

Recently, Over-the-Air (OTA) computation has emerged as a promising federated learning (FL) paradigm that leverages the waveform superposition properties of the wireless channel to realize fast model updates. Prior work focused on the OTA device ``pre-scaler" design under \emph{homogeneous} wireless conditions, in which devices experience the same average path loss, resulting in zero-bias solutions. Yet, zero-bias designs are limited by the device with the worst average path loss and hence may perform poorly in \emph{heterogeneous} wireless settings. In this scenario, there may be a benefit in designing \emph{biased} solutions, in exchange for a lower variance in the model updates. To optimize this trade-off, we study the design of OTA device pre-scalers by focusing on the OTA-FL convergence. We derive an upper bound on the model ``optimality error", which explicitly captures the effect of bias and variance in terms of the choice of the pre-scalers. Based on this bound, we identify two solutions of interest: minimum noise variance, and minimum noise variance zero-bias solutions. Numerical evaluations show that using OTA device pre-scalers that minimize the variance of FL updates, while allowing a small bias, can provide high gains over existing schemes.

Muhammad Faraz Ul Abrar, Nicolò Michelusi

Over-the-air (OTA) computation has recently emerged as a communication-efficient Federated Learning (FL) paradigm to train machine learning models over wireless networks. However, its performance is limited by the device with the worst SNR, resulting in fast yet noisy updates. On the other hand, allocating orthogonal resource blocks (RB) to individual devices via digital channels mitigates the noise problem, at the cost of increased communication latency. In this paper, we address this discrepancy and present ADFL, a novel Analog-Digital FL scheme: in each round, the parameter server (PS) schedules each device to either upload its gradient via the analog OTA scheme or transmit its quantized gradient over an orthogonal RB using the ``digital" scheme. Focusing on a single FL round, we cast the optimal scheduling problem as the minimization of the mean squared error (MSE) on the estimated global gradient at the PS, subject to a delay constraint, yielding the optimal device scheduling configuration and quantization bits for the digital devices. Our simulation results show that ADFL, by scheduling most of the devices in the OTA scheme while also occasionally employing the digital scheme for a few devices, consistently outperforms OTA-only and digital-only schemes, in both i.i.d. and non-i.i.d. settings.

Erik G. Larsson, Nicolo Michelusi

The decentralized gradient descent (DGD) algorithm, and its sibling, diffusion, are workhorses in decentralized machine learning, distributed inference and estimation, and multi-agent coordination. We propose a novel, principled framework for the analysis of DGD and diffusion for strongly convex, smooth objectives, and arbitrary undirected topologies, using contraction mappings coupled with a result called the mean Hessian theorem (MHT). The use of these tools yields tight convergence bounds, both in the noise-free and noisy regimes. While these bounds are qualitatively similar to results found in the literature, our approach using contractions together with the MHT decouples the algorithm dynamics (how quickly the algorithm converges to its fixed point) from its asymptotic convergence properties (how far the fixed point is from the global optimum). This yields a simple, intuitive analysis that is accessible to a broader audience. Extensions are provided to multiple local gradient updates, time-varying step sizes, noisy gradients (stochastic DGD and diffusion), communication noise, and random topologies.

Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. Larsson

Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of learning from streaming data through a time-varying optimization lens. Unlike prior works that focus on generic formulations, we introduce a structured, \emph{weight-based} formulation that explicitly captures the streaming-data origin of the time-varying objective, where at each time step, an agent aims to minimize a weighted average loss over all the past data samples. We focus on two specific weighting strategies: (1) uniform weights, which treat all samples equally, and (2) discounted weights, which geometrically decay the influence of older data. For both schemes, we derive tight bounds on the ``tracking error'' (TE), defined as the deviation between the model parameter and the time-varying optimum at a given time step, under gradient descent (GD) updates. We show that under uniform weighting, the TE vanishes asymptotically with a $\mathcal{O}(1/t)$ decay rate, whereas discounted weighting incurs a nonzero error floor controlled by the discount factor and the number of gradient updates performed at each time step. Our theoretical findings are validated through numerical simulations.

Manish Kumar, Tzu-Hsuan Chou, Byunghyun Lee et al.

Low-latency localization is critical in cellular networks to support real-time applications requiring precise positioning. In this paper, we propose a distributed machine learning (ML) framework for fingerprint-based localization tailored to cell-free massive multiple-input multiple-output (MIMO) systems, an emerging architecture for 6G networks. The proposed framework enables each access point (AP) to independently train a Gaussian process regression model using local angle-of-arrival and received signal strength fingerprints. These models provide probabilistic position estimates for the user equipment (UE), which are then fused by the UE with minimal computational overhead to derive a final location estimate. This decentralized approach eliminates the need for fronthaul communication between the APs and the central processing unit (CPU), thereby reducing latency. Additionally, distributing computational tasks across the APs alleviates the processing burden on the CPU compared to traditional centralized localization schemes. Simulation results demonstrate that the proposed distributed framework achieves localization accuracy comparable to centralized methods, despite lacking the benefits of centralized data aggregation. Moreover, it effectively reduces uncertainty of the location estimates, as evidenced by the 95\% covariance ellipse. The results highlight the potential of distributed ML for enabling low-latency, high-accuracy localization in future 6G networks.

Haifeng Wen, Nicolò Michelusi, Osvaldo Simeone et al.

Over-the-air federated learning (FL), i.e., AirFL, leverages computing primitively over multiple access channels. A long-standing challenge in AirFL is to achieve coherent signal alignment without relying on expensive channel estimation and feedback. This paper proposes NCAirFL, a CSI-free AirFL scheme based on unbiased non-coherent detection at the edge server. By exploiting binary dithering and a long-term memory based error-compensation mechanism, NCAirFL achieves a convergence rate of order $\mathcal{O}(1/\sqrt{T})$ in terms of the average square norm of the gradient for general non-convex and smooth objectives, where $T$ is the number of communication rounds. Experiments demonstrate the competitive performance of NCAirFL compared to vanilla FL with ideal communications and to coherent transmission-based benchmarks.

Seyyedali Hosseinalipour, Su Wang, Nicolo Michelusi et al.

Federated learning (FedL) has emerged as a popular technique for distributing model training over a set of wireless devices, via iterative local updates (at devices) and global aggregations (at the server). In this paper, we develop parallel successive learning (PSL), which expands the FedL architecture along three dimensions: (i) Network, allowing decentralized cooperation among the devices via device-to-device (D2D) communications. (ii) Heterogeneity, interpreted at three levels: (ii-a) Learning: PSL considers heterogeneous number of stochastic gradient descent iterations with different mini-batch sizes at the devices; (ii-b) Data: PSL presumes a dynamic environment with data arrival and departure, where the distributions of local datasets evolve over time, captured via a new metric for model/concept drift. (ii-c) Device: PSL considers devices with different computation and communication capabilities. (iii) Proximity, where devices have different distances to each other and the access point. PSL considers the realistic scenario where global aggregations are conducted with idle times in-between them for resource efficiency improvements, and incorporates data dispersion and model dispersion with local model condensation into FedL. Our analysis sheds light on the notion of cold vs. warmed up models, and model inertia in distributed machine learning. We then propose network-aware dynamic model tracking to optimize the model learning vs. resource efficiency tradeoff, which we show is an NP-hard signomial programming problem. We finally solve this problem through proposing a general optimization solver. Our numerical results reveal new findings on the interdependencies between the idle times in-between the global aggregations, model/concept drift, and D2D cooperation configuration.

David Nickel, Frank Po-Chen Lin, Seyyedali Hosseinalipour et al.

Federated learning (FL) has emerged as a popular technique for distributing machine learning across wireless edge devices. We examine FL under two salient properties of contemporary networks: device-server communication delays and device computation heterogeneity. Our proposed StoFedDelAv algorithm incorporates a local-global model combiner into the FL synchronization step. We theoretically characterize the convergence behavior of StoFedDelAv and obtain the optimal combiner weights, which consider the global model delay and expected local gradient error at each device. We then formulate a network-aware optimization problem which tunes the minibatch sizes of the devices to jointly minimize energy consumption and machine learning training loss, and solve the non-convex problem through a series of convex approximations. Our simulations reveal that StoFedDelAv outperforms the current art in FL, evidenced by the obtained improvements in optimization objective.

Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam et al.

Federated learning has emerged as a popular technique for distributing model training across the network edge. Its learning architecture is conventionally a star topology between the devices and a central server. In this paper, we propose two timescale hybrid federated learning (TT-HF), which migrates to a more distributed topology via device-to-device (D2D) communications. In TT-HF, local model training occurs at devices via successive gradient iterations, and the synchronization process occurs at two timescales: (i) macro-scale, where global aggregations are carried out via device-server interactions, and (ii) micro-scale, where local aggregations are carried out via D2D cooperative consensus formation in different device clusters. Our theoretical analysis reveals how device, cluster, and network-level parameters affect the convergence of TT-HF, and leads to a set of conditions under which a convergence rate of O(1/t) is guaranteed. Experimental results demonstrate the improvements in convergence and utilization that can be obtained by TT-HF over state-of-the-art federated learning baselines.

Nicolò Michelusi, Gesualdo Scutari, Chang-Shen Lee

This paper studies distributed algorithms for (strongly convex) composite optimization problems over mesh networks, subject to quantized communications. Instead of focusing on a specific algorithmic design, a black-box model is proposed, casting linearly convergent distributed algorithms in the form of fixed-point iterates. The algorithmic model is equipped with a novel random or deterministic Biased Compression (BC) rule on the quantizer design, and a new Adaptive encoding Nonuniform Quantizer (ANQ) coupled with a communication-efficient encoding scheme, which implements the BC-rule using a finite number of bits (below machine precision). This fills a gap existing in most state-of-the-art quantization schemes, such as those based on the popular compression rule, which rely on communication of some scalar signals with negligible quantization error (in practice quantized at the machine precision). A unified communication complexity analysis is developed for the black-box model, determining the average number of bits required to reach a solution of the optimization problem within a target accuracy. It is shown that the proposed BC-rule preserves linear convergence of the unquantized algorithms, and a trade-off between convergence rate and communication cost under ANQ-based quantization is characterized. Numerical results validate our theoretical findings and show that distributed algorithms equipped with the proposed ANQ have more favorable communication cost than algorithms using state-of-the-art quantization rules.

Bharath Keshavamurthy, Nicolo Michelusi

A novel LEarning-based Spectrum Sensing and Access (LESSA) framework is proposed, wherein a cognitive radio (CR) learns a time-frequency correlation model underlying spectrum occupancy of licensed users (LUs) in a radio ecosystem; concurrently, it devises an approximately optimal spectrum sensing and access policy under sensing constraints. A Baum-Welch algorithm is proposed to learn a parametric Markov transition model of LU spectrum occupancy based on noisy spectrum measurements. Spectrum sensing and access are cast as a Partially-Observable Markov Decision Process, approximately optimized via randomized point-based value iteration. Fragmentation, Hamming-distance state filters and Monte-Carlo methods are proposed to alleviate the inherent computational complexity, and a weighted reward metric to regulate the trade-off between CR throughput and LU interference. Numerical evaluations demonstrate that LESSA performs within 5 percent of a genie-aided upper bound with foreknowledge of LU spectrum occupancy, and outperforms state-of-the-art algorithms across the entire trade-off region: 71 percent over correlation-based clustering, 26 percent over Neyman-Pearson detection, 6 percent over the Viterbi algorithm, and 9 percent over an adaptive Deep Q-Network. LESSA is then extended to a distributed Multi-Agent setting (MA-LESSA), by proposing novel neighbor discovery and channel access rank allocation. MA-LESSA improves CR throughput by 43 percent over cooperative TD-SARSA, 84 percent over cooperative greedy distributed learning, and 3x over non-cooperative learning via g-statistics and ACKs. Finally, MA-LESSA is implemented on the DARPA SC2 platform, manifesting superior performance over competitors in a real-world TDWR-UNII WLAN emulation; its implementation feasibility is further validated on a testbed of ESP32 radios, exhibiting 96 percent success probability.

Muddassar Hussain, Nicolo Michelusi

Millimeter-wave vehicular networks incur enormous beam-training overhead to enable narrow-beam communications. This paper proposes a learning and adaptation framework in which the dynamics of the communication beams are learned and then exploited to design adaptive beam-tracking and training with low overhead: on a long-timescale, a deep recurrent variational autoencoder (DR-VAE) uses noisy beam-training feedback to learn a probabilistic model of beam dynamics and enable predictive beam-tracking; on a short-timescale, an adaptive beam-training procedure is formulated as a partially observable (PO-) Markov decision process (MDP) and optimized via point-based value iteration (PBVI) by leveraging beam-training feedback and a probabilistic prediction of the strongest beam pair provided by the DR-VAE. In turn, beam-training feedback is used to refine the DR-VAE via stochastic gradient ascent in a continuous process of learning and adaptation. The proposed DR-VAE learning framework learns accurate beam dynamics: it reduces the Kullback-Leibler divergence between the ground truth and the learned model of beam dynamics by 95% over the Baum-Welch algorithm and a naive learning approach that neglects feedback errors. Numerical results on a line-of-sight (LOS) scenario with multipath reveal that the proposed dual timescale approach yields near-optimal spectral efficiency, and improves it by 130% over a policy that scans exhaustively over the dominant beam pairs, and by 20% over a state-of-the-art POMDP policy. Finally, a low-complexity policy is proposed by reducing the POMDP to an error-robust MDP, and is shown to perform well in regimes with infrequent feedback errors.

Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam et al.

Federated learning has emerged as a popular technique for distributing machine learning (ML) model training across the wireless edge. In this paper, we propose two timescale hybrid federated learning (TT-HF), a semi-decentralized learning architecture that combines the conventional device-to-server communication paradigm for federated learning with device-to-device (D2D) communications for model training. In TT-HF, during each global aggregation interval, devices (i) perform multiple stochastic gradient descent iterations on their individual datasets, and (ii) aperiodically engage in consensus procedure of their model parameters through cooperative, distributed D2D communications within local clusters. With a new general definition of gradient diversity, we formally study the convergence behavior of TT-HF, resulting in new convergence bounds for distributed ML. We leverage our convergence bounds to develop an adaptive control algorithm that tunes the step size, D2D communication rounds, and global aggregation period of TT-HF over time to target a sublinear convergence rate of O(1/t) while minimizing network resource utilization. Our subsequent experiments demonstrate that TT-HF significantly outperforms the current art in federated learning in terms of model accuracy and/or network energy consumption in different scenarios where local device datasets exhibit statistical heterogeneity. Finally, our numerical evaluations demonstrate robustness against outages caused by fading channels, as well favorable performance with non-convex loss functions.

Frank Po-Chen Lin, Christopher G. Brinton, Nicolò Michelusi

Federated learning has received significant attention as a potential solution for distributing machine learning (ML) model training through edge networks. This work addresses an important consideration of federated learning at the network edge: communication delays between the edge nodes and the aggregator. A technique called FedDelAvg (federated delayed averaging) is developed, which generalizes the standard federated averaging algorithm to incorporate a weighting between the current local model and the delayed global model received at each device during the synchronization step. Through theoretical analysis, an upper bound is derived on the global model loss achieved by FedDelAvg, which reveals a strong dependency of learning performance on the values of the weighting and learning rate. Experimental results on a popular ML task indicate significant improvements in terms of convergence speed when optimizing the weighting scheme to account for delays.

Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton et al.

Federated learning has generated significant interest, with nearly all works focused on a "star" topology where nodes/devices are each connected to a central server. We migrate away from this architecture and extend it through the network dimension to the case where there are multiple layers of nodes between the end devices and the server. Specifically, we develop multi-stage hybrid federated learning (MH-FL), a hybrid of intra- and inter-layer model learning that considers the network as a multi-layer cluster-based structure. MH-FL considers the topology structures among the nodes in the clusters, including local networks formed via device-to-device (D2D) communications, and presumes a semi-decentralized architecture for federated learning. It orchestrates the devices at different network layers in a collaborative/cooperative manner (i.e., using D2D interactions) to form local consensus on the model parameters and combines it with multi-stage parameter relaying between layers of the tree-shaped hierarchy. We derive the upper bound of convergence for MH-FL with respect to parameters of the network topology (e.g., the spectral radius) and the learning algorithm (e.g., the number of D2D rounds in different clusters). We obtain a set of policies for the D2D rounds at different clusters to guarantee either a finite optimality gap or convergence to the global optimum. We then develop a distributed control algorithm for MH-FL to tune the D2D rounds in each cluster over time to meet specific convergence criteria. Our experiments on real-world datasets verify our analytical results and demonstrate the advantages of MH-FL in terms of resource utilization metrics.