Searcharxiv⌕ Search

arXiv subjects

Vincenzo Matta

Publications and source records attributed to Vincenzo Matta.

31 records · Page 2Linked to original sources
arXiv2019

Interplay between Topology and Social Learning over Weak Graphs

We consider a social learning problem, where a network of agents is interested in selecting one among a finite number of hypotheses. We focus on weakly-connected graphs where the network is partitioned into a sending part and a receiving part. The data collected by the agents might be heterogeneous. For example, some sub-networks might intentionally generate data from a fake hypothesis in order to influence other agents. The social learning task is accomplished via a diffusion strategy where each agent: i) updates individually its belief using its private data; ii) computes a new belief by exponentiating a linear combination of the log-beliefs of its neighbors. First, we examine what agents learn over weak graphs (social learning problem). We obtain analytical formulas for the beliefs at the different agents, which reveal how the agents' detection capability and the network topology interact to influence the beliefs. In particular, the formulas allow us to predict when a leader-follower behavior is possible, where some sending agents can control the mind of the receiving agents by forcing them to choose a particular hypothesis. Second, we consider the dual or reverse learning problem that reveals how agents learned: given a stream of beliefs collected at a receiving agent, we would like to discover the global influence that any sending component exerts on this receiving agent (topology learning problem). A remarkable and perhaps unexpected interplay between social and topology learning is observed: given $H$ hypotheses and $S$ sending components, topology learning can be feasible when $H\geq S$. The latter being only a necessary condition, we examine the feasibility of topology learning for two useful classes of problems. The analysis reveals that a critical element to enable faithful topology learning is the diversity in the statistical models of the sending sub-networks.

cs.MA↗
arXiv2019

Local Tomography of Large Networks under the Low-Observability Regime

This article studies the problem of reconstructing the topology of a network of interacting agents via observations of the state-evolution of the agents. We focus on the large-scale network setting with the additional constraint of $partial$ observations, where only a small fraction of the agents can be feasibly observed. The goal is to infer the underlying subnetwork of interactions and we refer to this problem as $local$ $tomography$. In order to study the large-scale setting, we adopt a proper stochastic formulation where the unobserved part of the network is modeled as an Erdös-Rényi random graph, while the observable subnetwork is left arbitrary. The main result of this work is establishing that, under this setting, local tomography is actually possible with high probability, provided that certain conditions on the network model are met (such as stability and symmetry of the network combination matrix). Remarkably, such conclusion is established under the $low$-$observability$ $regime$, where the cardinality of the observable subnetwork is fixed, while the size of the overall network scales to infinity.

cs.MA↗
arXiv2019

Topology Inference over Networks with Nonlinear Coupling

This work examines the problem of topology inference over discrete-time nonlinear stochastic networked dynamical systems. The goal is to recover the underlying digraph linking the network agents, from observations of their state-evolution. The dynamical law governing the state-evolution of the interacting agents might be nonlinear, i.e., the next state of an agent can depend nonlinearly on its current state and on the states of its immediate neighbors. We establish sufficient conditions that allow consistent graph learning over a special class of networked systems, namely, logistic-type dynamical systems.

cs.MA↗
arXiv2018

Signal Amplitude Estimation and Detection from Unlabeled Binary Quantized Samples

Signal amplitude estimation and detection from unlabeled quantized binary samples are studied, assuming that the order of the time indexes is completely unknown. First, maximum likelihood (ML) estimators are utilized to estimate both the permutation matrix and unknown signal amplitude under arbitrary, but known signal shape and quantizer thresholds. Sufficient conditions are provided under which an ML estimator can be found in polynomial time and an alternating maximization algorithm is proposed to solve the general problem via good initial estimates. In addition, the statistical identifiability of the model is studied. Furthermore, the generalized likelihood ratio test (GLRT) detector is adopted to detect the presence of signal. In addition, an accurate approximation to the probability of successful permutation matrix recovery is derived, and explicit expressions are provided to reveal the relationship between the number of signal samples and the number of quantizers. Finally, numerical simulations are performed to verify the theoretical results.

cs.IT↗
arXiv2017

Consistent Tomography under Partial Observations over Adaptive Networks

This work studies the problem of inferring whether an agent is directly influenced by another agent over an adaptive diffusion network. Agent i influences agent j if they are connected (according to the network topology), and if agent j uses the data from agent i to update its online statistic. The solution of this inference task is challenging for two main reasons. First, only the output of the diffusion learning algorithm is available to the external observer that must perform the inference based on these indirect measurements. Second, only output measurements from a fraction of the network agents is available, with the total number of agents itself being also unknown. The main focus of this article is ascertaining under these demanding conditions whether consistent tomography is possible, namely, whether it is possible to reconstruct the interaction profile of the observable portion of the network, with negligible error as the network size increases. We establish a critical achievability result, namely, that for symmetric combination policies and for any given fraction of observable agents, the interacting and non-interacting agent pairs split into two separate clusters as the network size increases. This remarkable property then enables the application of clustering algorithms to identify the interacting agents influencing the observations. We provide a set of numerical experiments that verify the results for finite network sizes and time horizons. The numerical experiments show that the results hold for asymmetric combination policies as well, which is particularly relevant in the context of causation.

cs.MA↗
arXiv2016

DDoS Attacks with Randomized Traffic Innovation: Botnet Identification Challenges and Strategies

Distributed Denial-of-Service (DDoS) attacks are usually launched through the $botnet$, an "army" of compromised nodes hidden in the network. Inferential tools for DDoS mitigation should accordingly enable an early and reliable discrimination of the normal users from the compromised ones. Unfortunately, the recent emergence of attacks performed at the application layer has multiplied the number of possibilities that a botnet can exploit to conceal its malicious activities. New challenges arise, which cannot be addressed by simply borrowing the tools that have been successfully applied so far to earlier DDoS paradigms. In this work, we offer basically three contributions: $i)$ we introduce an abstract model for the aforementioned class of attacks, where the botnet emulates normal traffic by continually learning admissible patterns from the environment; $ii)$ we devise an inference algorithm that is shown to provide a consistent (i.e., converging to the true solution as time progresses) estimate of the botnet possibly hidden in the network; and $iii)$ we verify the validity of the proposed inferential strategy over $real$ network traces.

cs.IT↗
arXiv2016

Compressed Sensing for Time-Frequency Gravitational Wave Data Analysis

The potential of compressed sensing for obtaining sparse time-frequency representations for gravitational wave data analysis is illustrated by comparison with existing methods, as regards i) shedding light on the fine structure of noise transients (glitches) in preparation of their classification, and ii) boosting the performance of waveform consistency tests in the detection of unmodeled transient gravitational wave signals using a network of detectors affected by unmodeled noise transient

astro-ph.IM↗
arXiv2016

Diffusion-Based Adaptive Distributed Detection: Steady-State Performance in the Slow Adaptation Regime

This work examines the close interplay between cooperation and adaptation for distributed detection schemes over fully decentralized networks. The combined attributes of cooperation and adaptation are necessary to enable networks of detectors to continually learn from streaming data and to continually track drifts in the state of nature when deciding in favor of one hypothesis or another. The results in the paper establish a fundamental scaling law for the steady-state probabilities of miss-detection and false-alarm in the slow adaptation regime, when the agents interact with each other according to distributed strategies that employ small constant step-sizes. The latter are critical to enable continuous adaptation and learning. The work establishes three key results. First, it is shown that the output of the collaborative process at each agent has a steady-state distribution. Second, it is shown that this distribution is asymptotically Gaussian in the slow adaptation regime of small step-sizes. And third, by carrying out a detailed large deviations analysis, closed-form expressions are derived for the decaying rates of the false-alarm and miss-detection probabilities. Interesting insights are gained. In particular, it is verified that as the step-size $μ$ decreases, the error probabilities are driven to zero exponentially fast as functions of $1/μ$, and that the error exponents increase linearly in the number of agents. It is also verified that the scaling laws governing errors of detection and errors of estimation over networks behave very differently, with the former having an exponential decay proportional to $1/μ$, while the latter scales linearly with decay proportional to $μ$. It is shown that the cooperative strategy allows each agent to reach the same detection performance, in terms of detection error exponents, of a centralized stochastic-gradient solution.

cs.IT↗
arXiv2016

Distributed Detection over Adaptive Networks: Refined Asymptotics and the Role of Connectivity

We consider distributed detection problems over adaptive networks, where dispersed agents learn continually from streaming data by means of local interactions. The simultaneous requirements of adaptation and cooperation are achieved by employing diffusion algorithms with constant step-size μ. In [1], [2] some main features of adaptive distributed detection were revealed. By resorting to large deviations analysis, it was established that the Type-I and Type-II error probabilities of all agents vanish exponentially as functions of 1/μ, and that all agents share the same Type-I and Type-II error exponents. However, numerical evidences presented in [1], [2] showed that the theory of large deviations does not capture the fundamental impact of network connectivity on performance, and that additional tools and efforts are required to obtain accurate predictions for the error probabilities. This work addresses these open issues and extends the results of [1], [2] in several directions. By conducting a refined asymptotic analysis based on the mathematical framework of exact asymptotics, we arrive at a revealing and powerful understanding of the universal behavior of distributed detection over adaptive networks: as functions of 1/μ, the error (log-)probability curves corresponding to different agents stay nearly-parallel to each other (as already discovered in [1], [2]), however, these curves are ordered following a criterion reflecting the degree of connectivity of each agent. Depending on the combination weights, the more connected an agent is, the lower its error probability curve will be. Interesting and somehow unexpected behaviors emerge, in terms of the interplay between the network topology, the combination weights, and the inference performance. The lesson learned is that connectivity matters.

cs.MA↗
arXiv2015

Sequential nonideal measurements of quantum oscillators: Statistical characterization with and without environmental coupling

A one-dimensional quantum oscillator is monitored by taking repeated position measurements. As a first con- tribution, it is shown that, under a quantum nondemolition measurement scheme applied to a system initially at the ground state, (i) the observed sequence of measurements (quantum tracks) corresponding to a single experiment converges to a limit point, and that (ii) the limit point is random over the ensemble of the experiments, being distributed as a zero-mean Gaussian random variable with a variance at most equal to the ground-state variance. As a second contribution, the richer scenario where the oscillator is coupled with a frozen (i.e., at the ground state) ensemble of independent quantum oscillators is considered. A sharply different behavior emerges: under the same measurement scheme, here we observe that the measurement sequences are essentially divergent. Such a rigorous statistical analysis of the sequential measurement process might be useful for characterizing the main quantities that are currently used for inference, manipulation, and monitoring of many quantum systems. Several interesting properties of the quantum tracks evolution, as well as of the associated (quantum) threshold crossing times, are discussed and the dependence upon the main system parameters (e.g., the choice of the measurement sampling time, the degree of interaction with the environment, the measurement device accuracy) is elucidated. At a more fundamental level, it is seen that, as an application of basic quantum mechanics principles, a sharp difference exists between the intrinsic randomness unavoidably present in any quantum system, and the extrinsic randomness arising from the environmental coupling, i.e., the randomness induced by an external source of disturbance.

quant-ph↗
arXiv2011

Asymptotic Properties of One-Bit Distributed Detection with Ordered Transmissions

Consider a sensor network made of remote nodes connected to a common fusion center. In a recent work Blum and Sadler [1] propose the idea of ordered transmissions -sensors with more informative samples deliver their messages first- and prove that optimal detection performance can be achieved using only a subset of the total messages. Taking to one extreme this approach, we show that just a single delivering allows making the detection errors as small as desired, for a sufficiently large network size: a one-bit detection scheme can be asymptotically consistent. The transmission ordering is based on the modulus of some local statistic (MO system). We derive analytical results proving the asymptotic consistency and, for the particular case that the local statistic is the log-likelihood (\ell-MO system), we also obtain a bound on the error convergence rate. All the theorems are proved under the general setup of random number of sensors. Computer experiments corroborate the analysis and address typical examples of applications including: non-homogeneous Poisson-deployed networks, detection by per-sensor censoring, monitoring of energy-constrained phenomenon.

cs.IT↗
arXiv2011

The Embedding Capacity of Information Flows Under Renewal Traffic

Given two independent point processes and a certain rule for matching points between them, what is the fraction of matched points over infinitely long streams? In many application contexts, e.g., secure networking, a meaningful matching rule is that of a maximum causal delay, and the problem is related to embedding a flow of packets in cover traffic such that no traffic analysis can detect it. We study the best undetectable embedding policy and the corresponding maximum flow rate ---that we call the embedding capacity--- under the assumption that the cover traffic can be modeled as arbitrary renewal processes. We find that computing the embedding capacity requires the inversion of very structured linear systems that, for a broad range of renewal models encountered in practice, admits a fully analytical expression in terms of the renewal function of the processes. Our main theoretical contribution is a simple closed form of such relationship. This result enables us to explore properties of the embedding capacity, obtaining closed-form solutions for selected distribution families and a suite of sufficient conditions on the capacity ordering. We evaluate our solution on real network traces, which shows a noticeable match for tight delay constraints. A gap between the predicted and the actual embedding capacities appears for looser constraints, and further investigation reveals that it is caused by inaccuracy of the renewal traffic model rather than of the solution itself.

cs.IT↗