VMVincenzo Matta

Vincenzo Matta

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Vincenzo Matta has a total of 1000 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Performance Evaluation of Social Learning

    by Felice Scala, Marco Carpentiero, Vincenzo Matta, Ali H. Sayed

  • Doubly Adaptive Social Learning

    by Marco Carpentiero, Virginia Bordignon, Vincenzo Matta, Ali H. Sayed

    In social learning, a network of agents assigns probability scores (beliefs) to some hypotheses of interest, which rule the generation of local streaming data observed by each agent. Belief formation takes place by means of an iterative two-step procedure where: i) the agents update locally their beliefs by using some likelihood models; and ii) the updated beliefs are combined with the beliefs of the neighboring agents, using a pooling rule. This procedure can fail to perform well in the presence of dynamic drifts, leading the agents to incorrect decision making. Here, we focus on the fully online setting where both the true hypothesis and the likelihood models can change over time. We propose the doubly adaptive social learning (A2 SL) strategy, which infuses social learning with the necessary adaptation capabilities. This goal is achieved by exploiting two adaptation stages: i) a stochastic gradient descent update to learn and track the drifts in the decision model; ii) and an adaptive belief update to track the true hypothesis changing over time. These stages are controlled by two adaptation parameters that govern the evolution of the error probability for each agent. We show that all agents learn consistently for sufficiently small adaptation parameters, in the sense that they ultimately place all their belief mass on the true hypothesis. In particular, the probability of choosing the wrong hypothesis converges to values on the order of the adaptation parameters. The theoretical analysis is illustrated both on synthetic data and by applying the A2 SL strategy to a social learning problem in the online setting using real data.

  • Adaptive Social Learning for Slow Markov Chains

    by Malek Khammassi, Virginia Bordignon, Vincenzo Matta, Ali H. Sayed

    This paper studies the problem of interconnected agents collaborating to track a dynamic state from partially informative observations, where the state follows a slow finite-state Markov chain. While the centralized version of this problem is well understood, the decentralized setting warrants further exploration. This work aims to demonstrate that a decentralized social learning strategy can achieve the same error probability scaling law in the rare transitions regime as the optimal centralized solution. To study this problem, we focus on adaptive social learning (ASL), a recent strategy developed for non-stationary environments, and analyze its performance when the agents’ observations are governed by a hidden, slow Markov chain. Our study yields two key findings. First, we demonstrate that the ASL adaptation performance is closely linked to the dynamics of the underlying Markov chain, achieving a vanishing steady-state error probability when the average drift time of the Markov chain exceeds the ASL adaptation time. Second, we derive a closed-form upper bound for the ASL steady-state error probability in the rare transition regime, showing that it decays similarly to the optimal centralized solution. Simulations illustrate our theoretical findings and provide a comparative analysis with existing strategies.

  • Open Access

    Doubly Adaptive Social Learning

    by Marco Carpentiero, Virginia Bordignon, Vincenzo Matta, Ali H. Sayed

    In social learning, a network of agents assigns probability scores (beliefs) to some hypotheses of interest, which rule the generation of local streaming data observed by each agent. Belief formation takes place by means of an iterative two-step procedure where: i) the agents update locally their beliefs by using some likelihood model; and ii) the updated beliefs are combined with the beliefs of the neighboring agents, using a pooling rule. This procedure can fail to perform well in the presence of dynamic drifts, leading the agents to incorrect decision making. Here, we focus on the fully online setting where both the true hypothesis and the likelihood models can change over time. We propose the doubly adaptive social learning ($\text{A}^2\text{SL}$) strategy, which infuses social learning with the necessary adaptation capabilities. This goal is achieved by exploiting two adaptation stages: i) a stochastic gradient descent update to learn and track the drifts in the decision model; ii) and an adaptive belief update to track the true hypothesis changing over time. These stages are controlled by two adaptation parameters that govern the evolution of the error probability for each agent. We show that all agents learn consistently for sufficiently small adaptation parameters, in the sense that they ultimately place all their belief mass on the true hypothesis. In particular, the probability of choosing the wrong hypothesis converges to values on the order of the adaptation parameters. The theoretical analysis is illustrated both on synthetic data and by applying the $\text{A}^2\text{SL}$ strategy to a social learning problem in the online setting using real data.

  • Differential Error Feedback for Communication-Efficient Decentralized Learning

    by Roula Nassif, Stefan Vlaski, Marco Carpentiero, Vincenzo Matta, Ali H. Sayed

    Communication-constrained algorithms for decentralized learning and optimization rely on local updates coupled with the exchange of compressed signals. In this context, differential quantization is an effective technique to mitigate the negative impact of compression by leveraging correlations between successive iterates. In addition, the use of error feedback, which consists of incorporating the compression error into subsequent steps, is a powerful mechanism to compensate for the bias caused by the compression. Under error feedback, performance guarantees in the literature have so far focused on algorithms employing a fusion center or a special class of contractive compressors that cannot be implemented with a finite number of bits. In this work, we propose a new decentralized communication-efficient learning approach that blends differential quantization with error feedback. The approach is specifically tailored for decentralized learning problems where agents have individual risk functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensional subspaces. This constrained formulation includes consensus or single-task optimization as special cases, and allows for more general task relatedness models such as multitask smoothness and coupled optimization. We show that, under some general conditions on the compression noise, and for sufficiently small step-sizes μ, the resulting communication-efficient strategy is stable both in terms of mean-square error and average bit rate: by reducing μ, it is possible to keep the estimation errors small (on the order of μ) without increasing indefinitely the bit rate as μ → 0. The results establish that, in the small step-size regime and with a finite number of bits, it is possible to attain the performance achievable in the absence of compression.


  • Social Learning: Opinion Formation and Decision-Making over Graphs

    by Vincenzo Matta, Virginia Bordignon, Ali H. Sayed

    Publishers of Foundations and Trends, making research accessible


  • Socially Intelligent Networks: A framework for decision making over graphs

    by Virginia Bordignon, Vincenzo Matta, Ali H. Sayed

    By “social learning,” in this article we refer to mechanisms for opinion formation and decision making over graphs and the study of how agents’ decisions evolve dynamically through interactions with neighbors and the environment. The study of social learning strategies is critical for at least two reasons. On one hand, it allows for a deeper understanding of the fundamental cognitive mechanisms that enable opinion formation over networks and the propagation of information or misinformation over them. On the other hand, these same learning strategies are effective for decision making by networked agents under challenging conditions, such as highly dynamic environments, nonstationary models and data, untruthful or malicious agents, sparsely connected graphs, and constrained communication. The article presents a unifying framework that covers several cases of interest, such as single-agent Bayesian learning, multiagent non-Bayesian learning, adaptive social learning, social machine learning, partial information sharing, influence discovery, and many others. The presentation highlights important limitations of the traditional social learning strategies. One limitation is the inability to track well drifting conditions. Traditional approaches lead to stubborn agents, which resist new states of information and are slow to react to changes in the environment, like an opinion that changes over time. Another limitation of the traditional strategies is that they assume perfect knowledge of the data models, which is seldom available in practice. The article illustrates recent advances that address these issues. We show how to endow multiagent networks with adaptation abilities and how to build social machine learning solutions that learn the necessary models directly from the data. These are fundamental steps toward the construction of socially intelligent networks, capable of exploiting cooperation and diversity across the agents to guarantee reliable learning performance under nonstationary, heterogeneous, and uncertain environments.


  • Open Access

    Compressed Regression Over Adaptive Networks

    by Marco Carpentiero, Vincenzo Matta, Ali H. Sayed

    In this work we derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints, a regression problem. Agents employ the recently proposed ACTC (adapt-compress-then-combine) diffusion strategy, where the signals exchanged locally by neighboring agents are encoded with randomized differential compression operators. We provide a detailed characterization of the mean-square estimation error, which is shown to comprise a term related to the error that agents would achieve without communication constraints, plus a term arising from compression. The analysis reveals quantitative relationships between the compression loss and fundamental attributes of the distributed regression problem, in particular, the stochastic approximation error caused by the gradient noise and the network topology (through the Perron eigenvector). We show that knowledge of such relationships is critical to allocate optimally the communication resources across the agents, taking into account their individual attributes, such as the quality of their data or their degree of centrality in the network topology. We devise an optimized allocation strategy where the parameters necessary for the optimization can be learned online by the agents. Illustrative examples show that a significant performance improvement, as compared to a blind (i.e., uniform) resource allocation, can be achieved by optimizing the allocation by means of the provided mean-square-error formulas


  • Open Access

    Distributed Adaptive Learning Under Communication Constraints

    by Marco Carpentiero, Vincenzo Matta, Ali H. Sayed

    We consider a network of agents that must solve an online optimization problem from continual observation of streaming data. To this end, the agents implement a distributed cooperative strategy where each agent is allowed to perform local exchange of information with its neighbors. In order to cope with communication constraints, the exchanged information must be compressed to reduce the communication load. We propose a distributed diffusion strategy nicknamed as ACTC (Adapt-Compress-Then-Combine), which implements the following three operations: adaptation, where each agent performs an individual stochastic-gradient update; compression, which leverages a recently introduced class of stochastic compression operators; and combination, where each agent combines the compressed updates received from its neighbors. The main elements of novelty of this work are as follows: i) adaptive strategies, where constant (as opposed to diminishing) step-sizes are critical to infuse the agents with the ability of responding in real time to nonstationary variations in the observed model; ii) directed, i.e., non-symmetric combination policies, which allow us to enhance the role played by the network topology in the learning performance; iii) global strong convexity, a condition under which the individual agents might feature even non-convex cost functions. Under this demanding setting, we establish that the iterates of the ACTC strategy fluctuate around the exact global optimizer with a mean-square-deviation on the order of the step-size, achieving remarkable savings of communication resources. Comparison against up-to-date learning strategies with compressed data highlights the benefits of the proposed solution.


  • Memory-Aware Social Learning Under Partial Information Sharing

    by Michele Cirillo, Virginia Bordignon, Vincenzo Matta, Ali H. Sayed

    This work examines a social learning problem, where dispersed agents connected through a network topology interact locally to form their opinions ( beliefs ) as regards certain hypotheses of interest. These opinions evolve over time, since the agents collect observations from the environment, and update their current beliefs by accounting for: their past beliefs, the innovation contained in the new data, and the beliefs received from the neighbors. The distinguishing feature of the present work is that agents are constrained to share opinions regarding only a single hypothesis. We devise a novel learning strategy where each agent forms a valid belief by completing the partial beliefs received from its neighbors. This completion is performed by exploiting the knowledge accumulated in the past beliefs, thanks to a principled memory-aware rule inspired by a Bayesian criterion. The analysis allows us to characterize the role of memory in social learning under partial information sharing , revealing novel and nontrivial learning dynamics. Surprisingly, we establish that the standard classification rule based on selecting the maximum belief is not optimal under partial information sharing, while there exists a consistent threshold-based decision rule that allows each agent to classify correctly the hypothesis of interest. We also show that the proposed strategy outperforms previously considered schemes, highlighting that the introduction of memory in the social learning algorithm is critical to overcome the limitations arising from sharing partial information.