arXiv subjects

Joao Xavier

Publications and source records attributed to Joao Xavier.

At least 19 recordsLinked to original sources

arXiv2020

Primal-dual methods for large-scale and distributed convex optimization and data analytics

The augmented Lagrangian method (ALM) is a classical optimization tool that solves a given "difficult" (constrained) problem via finding solutions of a sequence of "easier"(often unconstrained) sub-problems with respect to the original (primal) variable, wherein constraints satisfaction is controlled via the so-called dual variables. ALM is highly flexible with respect to how primal sub-problems can be solved, giving rise to a plethora of different primal-dual methods. The powerful ALM mechanism has recently proved to be very successful in various large scale and distributed applications. In addition, several significant advances have appeared, primarily on precise complexity results with respect to computational and communication costs in the presence of inexact updates and design and analysis of novel optimal methods for distributed consensus optimization. We provide a tutorial-style introduction to ALM and its variants for solving convex optimization problems in large scale and distributed settings. We describe control-theoretic tools for the algorithms' analysis and design, survey recent results, and provide novel insights in the context of two emerging applications: federated learning and distributed energy trading.

math.OC↗

arXiv2015

From Weak Learning to Strong Learning in Fictitious Play Type Algorithms

The paper studies the highly prototypical Fictitious Play (FP) algorithm, as well as a broad class of learning processes based on best-response dynamics, that we refer to as FP-type algorithms. A well-known shortcoming of FP is that, while players may learn an equilibrium strategy in some abstract sense, there are no guarantees that the period-by-period strategies generated by the algorithm actually converge to equilibrium themselves. This issue is fundamentally related to the discontinuous nature of the best response correspondence and is inherited by many FP-type algorithms. Not only does it cause problems in the interpretation of such algorithms as a mechanism for economic and social learning, but it also greatly diminishes the practical value of these algorithms for use in distributed control. We refer to forms of learning in which players learn equilibria in some abstract sense only (to be defined more precisely in the paper) as weak learning, and we refer to forms of learning where players' period-by-period strategies converge to equilibrium as strong learning. An approach is presented for modifying an FP-type algorithm that achieves weak learning in order to construct a variant that achieves strong learning. Theoretical convergence results are proved.

math.OC↗

arXiv2015

On Robustness Properties in Empirical Centroid Fictitious Play

Empirical Centroid Fictitious Play (ECFP) is a generalization of the well-known Fictitious Play (FP) algorithm designed for implementation in large-scale games. In ECFP, the set of players is subdivided into equivalence classes with players in the same class possessing similar properties. Players choose a next-stage action by tracking and responding to aggregate statistics related to each equivalence class. This setup alleviates the difficult task of tracking and responding to the statistical behavior of every individual player, as is the case in traditional FP. Aside from ECFP, many useful modifications have been proposed to classical FP, e.g., rules allowing for network-based implementation, increased computational efficiency, and stronger forms of learning. Such modifications tend to be of great practical value; however, their effectiveness relies heavily on two fundamental properties of FP: robustness to alterations in the empirical distribution step size process, and robustness to best-response perturbations. The main contribution of the paper is to show that similar robustness properties also hold for the ECFP algorithm. This result serves as a first step in enabling practical modifications to ECFP, similar to those already developed for FP.

math.OC↗

arXiv2014

Distributed, simple and stable network localization

We propose a simple, stable and distributed algorithm which directly optimizes the nonconvex maximum likelihood criterion for sensor network localization, with no need to tune any free parameter. We reformulate the problem to obtain a gradient Lipschitz cost; by shifting to this cost function we enable a Majorization-Minimization (MM) approach based on quadratic upper bounds that decouple across nodes; the resulting algorithm happens to be distributed, with all nodes working in parallel. Our method inherits the MM stability: each communication cuts down the cost function. Numerical simulations indicate that the proposed approach tops the performance of the state of the art algorithm, both in accuracy and communication cost.

math.OC↗

arXiv2014

Fast Distributed Gradient Methods

We study distributed optimization problems when $N$ nodes minimize the sum of their individual costs subject to a common vector variable. The costs are convex, have Lipschitz continuous gradient (with constant $L$), and bounded gradient. We propose two fast distributed gradient algorithms based on the centralized Nesterov gradient algorithm and establish their convergence rates in terms of the per-node communications $\mathcal{K}$ and the per-node gradient evaluations $k$. Our first method, Distributed Nesterov Gradient, achieves rates $O\left({\log \mathcal{K}}/{\mathcal{K}}\right)$ and $O\left({\log k}/{k}\right)$. Our second method, Distributed Nesterov gradient with Consensus iterations, assumes at all nodes knowledge of $L$ and $μ(W)$ -- the second largest singular value of the $N \times N$ doubly stochastic weight matrix $W$. It achieves rates $O\left({1}/{\mathcal{K}^{2-ξ}}\right)$ and $O\left({1}/{k^2}\right)$ ($ξ>0$ arbitrarily small). Further, we give with both methods explicit dependence of the convergence constants on $N$ and $W$. Simulation examples illustrate our findings.

cs.IT↗

arXiv2014

Linear Convergence Rate of a Class of Distributed Augmented Lagrangian Algorithms

We study distributed optimization where nodes cooperatively minimize the sum of their individual, locally known, convex costs $f_i(x)$'s, $x \in {\mathbb R}^d$ is global. Distributed augmented Lagrangian (AL) methods have good empirical performance on several signal processing and learning applications, but there is limited understanding of their convergence rates and how it depends on the underlying network. This paper establishes globally linear (geometric) convergence rates of a class of deterministic and randomized distributed AL methods, when the $f_i$'s are twice continuously differentiable and have a bounded Hessian. We give explicit dependence of the convergence rates on the underlying network parameters. Simulations illustrate our analytical findings.

cs.IT↗

arXiv2013

Convergence Rates of Distributed Nesterov-like Gradient Methods on Random Networks

We consider distributed optimization in random networks where N nodes cooperatively minimize the sum \sum_{i=1}^N f_i(x) of their individual convex costs. Existing literature proposes distributed gradient-like methods that are computationally cheap and resilient to link failures, but have slow convergence rates. In this paper, we propose accelerated distributed gradient methods that: 1) are resilient to link failures; 2) computationally cheap; and 3) improve convergence rates over other gradient methods. We model the network by a sequence of independent, identically distributed random matrices {W(k)} drawn from the set of symmetric, stochastic matrices with positive diagonals. The network is connected on average and the cost functions are convex, differentiable, with Lipschitz continuous and bounded gradients. We design two distributed Nesterov-like gradient methods that modify the D-NG and D-NC methods that we proposed for static networks. We prove their convergence rates in terms of the expected optimality gap at the cost function. Let k and K be the number of per-node gradient evaluations and per-node communications, respectively. Then the modified D-NG achieves rates O(log k/k) and O(\log K/K), and the modified D-NC rates O(1/k^2) and O(1/K^{2-ξ}), where ξ>0 is arbitrarily small. For comparison, the standard distributed gradient method cannot do better than Ω(1/k^{2/3}) and Ω(1/K^{2/3}), on the same class of cost functions (even for static networks). Simulation examples illustrate our analytical findings.

cs.IT↗

arXiv2013

Empirical Centroid Fictitious Play: An Approach For Distributed Learning In Multi-Agent Games

The paper is concerned with distributed learning in large-scale games. The well-known fictitious play (FP) algorithm is addressed, which, despite theoretical convergence results, might be impractical to implement in large-scale settings due to intense computation and communication requirements. An adaptation of the FP algorithm, designated as the empirical centroid fictitious play (ECFP), is presented. In ECFP players respond to the centroid of all players' actions rather than track and respond to the individual actions of every player. Convergence of the ECFP algorithm in terms of average empirical frequency (a notion made precise in the paper) to a subset of the Nash equilibria is proven under the assumption that the game is a potential game with permutation invariant potential function. A more general formulation of ECFP is then given (which subsumes FP as a special case) and convergence results are given for the class of potential games. Furthermore, a distributed formulation of the ECFP algorithm is presented, in which, players endowed with a (possibly sparse) preassigned communication graph, engage in local, non-strategic information exchange to eventually agree on a common equilibrium. Convergence results are proven for the distributed ECFP algorithm.

math.OC↗

arXiv2012

DCOOL-NET: Distributed cooperative localization for sensor networks

We present DCOOL-NET, a scalable distributed in-network algorithm for sensor network localization based on noisy range measurements. DCOOL-NET operates by parallel, collaborative message passing between single-hop neighbor sensors, and involves simple computations at each node. It stems from an application of the majorization-minimization (MM) framework to the nonconvex optimization problem at hand, and capitalizes on a novel convex majorizer. The proposed majorizer is endowed with several desirable properties and represents a key contribution of this work. It is a more accurate match to the underlying nonconvex cost function than popular MM quadratic majorizers, and is readily amenable to distributed minimization via the alternating direction method of multipliers (ADMM). Moreover, it allows for low-complexity, fast Nesterov gradient methods to tackle the ADMM subproblems induced at each node. Computer simulations show that DCOOL-NET achieves comparable or better sensor position accuracies than a state-of-art method which, furthermore, is not parallel.

math.OC↗

arXiv2012

Large Deviations Performance of Consensus+Innovations Distributed Detection with Non-Gaussian Observations

We establish the large deviations asymptotic performance (error exponent) of consensus+innovations distributed detection over random networks with generic (non-Gaussian) sensor observations. At each time instant, sensors 1) combine theirs with the decision variables of their neighbors (consensus) and 2) assimilate their new observations (innovations). This paper shows for general non-Gaussian distributions that consensus+innovations distributed detection exhibits a phase transition behavior with respect to the network degree of connectivity. Above a threshold, distributed is as good as centralized, with the same optimal asymptotic detection performance, but, below the threshold, distributed detection is suboptimal with respect to centralized detection. We determine this threshold and quantify the performance loss below threshold. Finally, we show the dependence of the threshold and performance on the distribution of the observations: distributed detectors over the same random network, but with different observations' distributions, for example, Gaussian, Laplace, or quantized, may have different asymptotic performance, even when the corresponding centralized detectors have the same asymptotic performance.

cs.IT↗

arXiv2012

Consensus and Products of Random Stochastic Matrices: Exact Rate for Convergence in Probability

Distributed consensus and other linear systems with system stochastic matrices $W_k$ emerge in various settings, like opinion formation in social networks, rendezvous of robots, and distributed inference in sensor networks. The matrices $W_k$ are often random, due to, e.g., random packet dropouts in wireless sensor networks. Key in analyzing the performance of such systems is studying convergence of matrix products $W_kW_{k-1}... W_1$. In this paper, we find the exact exponential rate $I$ for the convergence in probability of the product of such matrices when time $k$ grows large, under the assumption that the $W_k$'s are symmetric and independent identically distributed in time. Further, for commonly used random models like with gossip and link failure, we show that the rate $I$ is found by solving a min-cut problem and, hence, easily computable. Finally, we apply our results to optimally allocate the sensors' transmission power in consensus+innovations distributed detection.

math.PR↗

arXiv2011

Distributed Detection over Noisy Networks: Large Deviations Analysis

We study the large deviations performance of consensus+innovations distributed detection over noisy networks, where sensors at a time step k cooperate with immediate neighbors (consensus) and assimilate their new observations (innovation.) We show that, even under noisy communication, \emph{all sensors} can achieve exponential decay e^{-k C_{\mathrm{dis}}} of the detection error probability, even when certain (or most) sensors cannot detect the event of interest in isolation. We achieve this by designing a single time scale stochastic approximation type distributed detector with the optimal weight sequence {α_k}, by which sensors weigh their neighbors' messages. The optimal design of {α_k} balances the opposing effects of communication noise and information flow from neighbors: larger, slowly decaying α_k improves information flow but injects more communication noise. Further, we quantify the best achievable C_{\mathrm{dis}} as a function of the sensing signal and noise, communication noise, and network connectivity. Finally, we find a threshold on the communication noise power below which a sensor that can detect the event in isolation still improves its detection by cooperation through noisy links.

cs.IT↗

arXiv2011

Cooperative Convex Optimization in Networked Systems: Augmented Lagrangian Algorithms with Directed Gossip Communication

We study distributed optimization in networked systems, where nodes cooperate to find the optimal quantity of common interest, x=x^\star. The objective function of the corresponding optimization problem is the sum of private (known only by a node,) convex, nodes' objectives and each node imposes a private convex constraint on the allowed values of x. We solve this problem for generic connected network topologies with asymmetric random link failures with a novel distributed, decentralized algorithm. We refer to this algorithm as AL-G (augmented Lagrangian gossiping,) and to its variants as AL-MG (augmented Lagrangian multi neighbor gossiping) and AL-BG (augmented Lagrangian broadcast gossiping.) The AL-G algorithm is based on the augmented Lagrangian dual function. Dual variables are updated by the standard method of multipliers, at a slow time scale. To update the primal variables, we propose a novel, Gauss-Seidel type, randomized algorithm, at a fast time scale. AL-G uses unidirectional gossip communication, only between immediate neighbors in the network and is resilient to random link failures. For networks with reliable communication (i.e., no failures,) the simplified, AL-BG (augmented Lagrangian broadcast gossiping) algorithm reduces communication, computation and data storage cost. We prove convergence for all proposed algorithms and demonstrate by simulations the effectiveness on two applications: l_1-regularized logistic regression for classification and cooperative spectrum sensing for cognitive radio networks.

cs.IT↗

arXiv2010

Distributed Detection over Random Networks: Large Deviations Performance Analysis

We study the large deviations performance, i.e., the exponential decay rate of the error probability, of distributed detection algorithms over random networks. At each time step $k$ each sensor: 1) averages its decision variable with the neighbors' decision variables; and 2) accounts on-the-fly for its new observation. We show that distributed detection exhibits a "phase change" behavior. When the rate of network information flow (the speed of averaging) is above a threshold, then distributed detection is asymptotically equivalent to the optimal centralized detection, i.e., the exponential decay rate of the error probability for distributed detection equals the Chernoff information. When the rate of information flow is below a threshold, distributed detection achieves only a fraction of the Chernoff information rate; we quantify this achievable rate as a function of the network rate of information flow. Simulation examples demonstrate our theoretical findings on the behavior of distributed detection over random networks.

cs.IT↗

arXiv2010

Sensor Selection for Event Detection in Wireless Sensor Networks

We consider the problem of sensor selection for event detection in wireless sensor networks (WSNs). We want to choose a subset of p out of n sensors that yields the best detection performance. As the sensor selection optimality criteria, we propose the Kullback-Leibler and Chernoff distances between the distributions of the selected measurements under the two hypothesis. We formulate the maxmin robust sensor selection problem to cope with the uncertainties in distribution means. We prove that the sensor selection problem is NP hard, for both Kullback-Leibler and Chernoff criteria. To (sub)optimally solve the sensor selection problem, we propose an algorithm of affordable complexity. Extensive numerical simulations on moderate size problem instances (when the optimum by exhaustive search is feasible to compute) demonstrate the algorithm's near optimality in a very large portion of problem instances. For larger problems, extensive simulations demonstrate that our algorithm outperforms random searches, once an upper bound on computational time is set. We corroborate numerically the validity of the Kullback-Leibler and Chernoff sensor selection criteria, by showing that they lead to sensor selections nearly optimal both in the Neyman-Pearson and Bayes sense.

cs.IT↗

arXiv2010

Distributed Detection over Random Networks: Large Deviations Analysis

We show by large deviations theory that the performance of running consensus is asymptotically equivalent to the performance of the (asymptotically) optimal centralized detector. Running consensus is a stochastic approximation type algorithm for distributed detection in sensor networks, recently proposed. At each time step, the state at each sensor is updated by a local averaging of its own state and the states of its neighbors (consensus) and by accounting for the new observations (innovation). We assume Gaussian, spatially correlated observations, and we allow for the underlying network to be randomly varying. This paper shows through large deviations that the Bayes probability of detection error, for the distributed detector, decays at the best achievable rate, namely, the Chernoff information rate. Numerical examples illustrate the behavior of the distributed detector for finite number of observations.

cs.IT↗

arXiv2010

Distributed Detection over Time Varying Networks: Large Deviations Analysis

We apply large deviations theory to study asymptotic performance of running consensus distributed detection in sensor networks. Running consensus is a stochastic approximation type algorithm, recently proposed. At each time step k, the state at each sensor is updated by a local averaging of the sensor's own state and the states of its neighbors (consensus) and by accounting for the new observations (innovation). We assume Gaussian, spatially correlated observations. We allow the underlying network be time varying, provided that the graph that collects the union of links that are online at least once over a finite time window is connected. This paper shows through large deviations that, under stated assumptions on the network connectivity and sensors' observations, the running consensus detection asymptotically approaches in performance the optimal centralized detection. That is, the Bayes probability of detection error (with the running consensus detector) decays exponentially to zero as k goes to infinity at the Chernoff information rate-the best achievable rate of the asymptotically optimal centralized detector.

cs.IT↗

arXiv2009

Consensus in Correlated Random Topologies: Weights for Finite Time Horizon

We consider the weight design problem for the consensus algorithm under a finite time horizon. We assume that the underlying network is random where the links fail at each iteration with certain probability and the link failures can be spatially correlated. We formulate a family of weight design criteria (objective functions) that minimize n, n = 1,...,N (out of N possible) largest (slowest) eigenvalues of the matrix that describes the mean squared consensus error dynamics. We show that the objective functions are convex; hence, globally optimal weights (with respect to the design criteria) can be efficiently obtained. Numerical examples on large scale, sparse random networks with spatially correlated link failures show that: 1) weights obtained according to our criteria lead to significantly faster convergence than the choices available in the literature; 2) different design criteria that corresponds to different n, exhibits very interesting tradeoffs: faster transient performance leads to slower long time run performance and vice versa. Thus, n is a valuable degree of freedom and can be appropriately selected for the given time horizon.

cs.IT↗