本文研究局部归一化算法背景下的矩阵缩放过程及其收敛行为。作者从经典 Sinkhorn 算法出发，提出一种推广形式：每一步仅归一化单行或单列，且对更新顺序没有限制。他们扩展了 Birkhoff 定理，以刻画这些算法的收敛性质，尤其是在归一化序列任意时的性质。论文还探索了一种新颖应用，即在有向图上进行 Decentralized Random Walk（DRW，去中心化随机游走），其中智能体在没有全局知识或记忆的情况下局部修改边权重。本文表明，此类局部更新会收敛到一个双随机矩阵，从而确保图顶点上具有均匀的平稳分布。这些结果不仅深化了对矩阵缩放的理论理解，也为网络中的分布式和基于智能体的模型开辟了途径。
英文摘要：
This paper investigates matrix scaling processes in the context of local normalization algorithms and their convergence behavior. Starting from the classical Sinkhorn algorithm, the authors introduce a generalization where only a single row or column is normalized at each step, without restrictions on the update order. They extend Birkhoff's theorem to characterize the convergence properties of these algorithms, especially when the normalization sequence is arbitrary. A novel application is explored in the form of a Decentralized Random Walk (DRW) on directed graphs, where agents modify edge weights locally without global knowledge or memory. The paper shows that such local updates lead to convergence towards a doubly stochastic matrix, ensuring a uniform stationary distribution across graph vertices. These results not only deepen the theoretical understanding of matrix scaling but also open avenues for distributed and agent-based models in networks.
In this paper, we consider distributed optimization design for resource allocation problems over weight-balanced graphs. With the help of singular perturbation analysis, we propose a simple sub-optimal continuous-time optimization algorithm. Moreover, we prove the existence and uniqueness of the algorithm equilibrium, and then show the convergence with an exponential rate. Finally, we verify the sub-optimality of the algorithm, which can approach the optimal solution as an adjustable parameter tends to zero.
In this paper, the distributed resource allocation problem on strongly connected and weight-balanced digraphs is investigated, where the decisions of each agent are restricted to satisfy the coupled network resource constraints and heterogeneous general convex sets. Moreover, the local cost function can be non-smooth. In order to achieve the exact optimum of the nonsmooth resource allocation problem, a novel continuous-time distributed algorithm based on the gradient descent scheme and differentiated projection operators is proposed. With the help of the set-valued LaSalle invariance principle…
The optimal power flow (OPF) problem is fundamental in power system operations and planning. Large-scale renewable penetration in distribution networks calls for real-time feedback control, and hence the need for fast and distributed solutions for OPF. This is difficult because OPF is nonconvex and Kirchhoff's laws are global. In this paper we propose a solution for balanced radial distribution networks. It exploits recent results that suggest solving for a globally optimal solution of OPF over a radial network through the second-order cone program (SOCP) relaxation. Our distributed algorithm …
In this paper, a distributed optimization problem is investigated via input feedforward passivity. First, an input-feedforward-passivity-based continuous-time distributed algorithm is proposed. It is shown that the error system of the proposed algorithm can be decomposed into a group of individual input feedforward passive (IFP) systems that interact with each other using output feedback information. Based on this IFP framework, convergence conditions of a suitable coupling gain are derived over weight-balanced and uniformly jointly strongly connected (UJSC) topologies. It is also shown that t…
Privacy preservation is becoming an increasingly important issue in data mining and machine learning. In this paper, we consider the privacy preserving features of distributed subgradient optimization algorithms. We first show that a well-known distributed subgradient synchronous optimization algorithm, in which all agents make their optimization updates simultaneously at all times, is not privacy preserving in the sense that the malicious agent can learn other agents' subgradients asymptotically. Then we propose a distributed subgradient projection asynchronous optimization algorithm without …
In distributed optimization for large-scale learning, a major performance limitation comes from the communications between the different entities. When computations are performed by workers on local data while a coordinator machine coordinates their updates to minimize a global loss, we present an asynchronous optimization algorithm that efficiently reduces the communications between the coordinator and workers. This reduction comes from a random sparsification of the local updates. We show that this algorithm converges linearly in the strongly convex case and also identifies optimal strongly …
In this paper, a centralized two-block separable optimization is considered for which a fully parallel primal-dual discrete-time algorithm with fixed step size is derived based on monotone operator splitting method. In this algorithm, the primal variables are updated in an alternating fashion like Alternating Direction Method of Multipliers (ADMM). However, unlike existing discrete-time algorithms such as Method of Multipliers (MM), ADMM, Bi-Alternating Direction Method of Multipliers (BiADMM), and Primal-Dual Fixed Point (PDFP) algorithms, that all suffer from sequential updates, all primal a…
In this paper, we propose a novel primal-dual proximal splitting algorithm (PD-PSA), named BALPA, for the composite optimization problem with equality constraints, where the loss function consists of a smooth term and a nonsmooth term composed with a linear mapping. In BALPA, the dual update is designed as a proximal point for a time-varying quadratic function, which balances the implementation of primal and dual update and retains the proximity-induced feature of classic PD-PSAs. In addition, by this balance, BALPA eliminates the inefficiency of classic PD-PSAs for composite optimization prob…
We consider distributed learning problem in games with an unknown cost-relevant parameter, and aim to find the Nash equilibrium while learning the true parameter. Inspired by the social learning literature, we propose a distributed non-Bayesian rule to learn the parameter (each agent maintains a belief on the parameter and updates the belief according to the received noisy cost), combined with best response dynamics for strategy update. The difficulty of the analysis lies mainly in the fact that the parameter learning process and strategy update process are coupled. We first prove that agents'…
Multi agent consensus algorithms with update steps based on so-called balanced asymmetric chains, are analyzed. For such algorithms it is shown that (i) the set of accumulation points of states is finite, (ii) the asymptotic unconditional occurrence of single consensus or multiple consensuses is directly related to the property of absolute infinite flow for the underlying update chain. The results are applied to well known consensus models.
Linear Convergence Rate Analysis of a Class of Exact First-Order Distributed Methods for Weight-Balanced Time-Varying Networks and Uncoordinated Step Sizes
Alma Mater Studiorum Università di Bologna（博洛尼亚大学）
In this paper we deal with a network of computing agents with local processing and neighboring communication capabilities that aim at solving (without any central unit) a submodular optimization problem. The cost function is the sum of many local submodular functions and each agent in the network has access to one function in the sum only. In this \emph{distributed} set-up, in order to preserve their own privacy, agents communicate with neighbors but do not share their local cost functions. We propose a distributed algorithm in which agents resort to the Lovàsz extension of their local submodu…
We propose a new belief update rule for Distributed Non-Bayesian learning in time-varying directed graphs, where a group of agents tries to collectively identify a hypothesis that best describes a sequence of observed data. We show that the proposed update rule, inspired by the Push-Sum algorithm, is consistent, moreover we provide an explicit characterization of its convergence rate. Our main result states that, after a transient time, all agents will concentrate their beliefs at a network independent rate. Network independent rates were not available for other consensus based distributed lea…
Semnan University（塞姆南大学）；Aalto University（阿尔托大学）；Georgia State University（佐治亚州立大学）；Tufts University（塔夫茨大学）
In this paper, we consider the binary classification problem via distributed Support-Vector-Machines (SVM), where the idea is to train a network of agents, with limited share of data, to cooperatively learn the SVM classifier for the global database. Agents only share processed information regarding the classifier parameters and the gradient of the local loss functions instead of their raw data. In contrast to the existing work, we propose a continuous-time algorithm that incorporates network topology changes in discrete jumps. This hybrid nature allows us to remove chattering that arises beca…
We consider the consensual distributed optimization problem and propose an asynchronous version of the Alternating Direction Method of Multipliers (ADMM) algorithm to solve it. The `asynchronous' part here refers to the fact that only one node/processor is updated (i.e. performs a minimization step) at each iteration of the algorithm. The selection of the node to be updated is decided by simulating a Markov chain. The proposed algorithm is shown to have a linear convergence property in expectation for the class of functions which are strongly convex and continuously differentiable.
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（脸书人工智能研究院）
Distributed optimization is essential for training large models on large datasets. Multiple approaches have been proposed to reduce the communication overhead in distributed training, such as synchronizing only after performing multiple local SGD steps, and decentralized methods (e.g., using gossip algorithms) to decouple communications among workers. Although these methods run faster than AllReduce-based methods, which use blocking communication before every update, the resulting models may be less accurate after the same number of updates. Inspired by the BMUF method of Chen & Huo (2016), we…
Non-concave maximization has been the subject of much recent study in the optimization and machine learning communities, specifically in deep learning. Recent papers Ge et al, Lee et al (and references therein) indicate that first order methods work well and avoid saddle points. Results as in Lee et al, however, are limited to the \textit{unconstrained} case or for cases where the critical points are in the interior of the feasibility set, which fail to capture some of the most interesting applications. In this paper we focus on \textit{constrained} non-concave maximization. We analyze a varia…
This paper considers a nested stochastic distributed optimization problem. In it, approximate solutions to realizations of the inner-problem are leveraged to obtain a Distributed Stochastic Cubic Regularized Newton (DiSCRN) update to the decision variable of the outer problem. We provide an example involving electric vehicle users with various preferences which demonstrates that this model is appropriate and sufficiently complex for a variety of data-driven multi-agent settings, in contrast to non-nested models. The main two contributions of the paper are: (i) development of local stopping cri…
Nonnegative matrix factorization (NMF) has attracted much attention in the last decade as a dimension reduction method in many applications. Due to the explosion in the size of data, naturally the samples are collected and stored distributively in local computational nodes. Thus, there is a growing need to develop algorithms in a distributed memory architecture. We propose a novel distributed algorithm, called \textit{distributed incremental block coordinate descent} (DID), to solve the problem. By adapting the block coordinate descent framework, closed-form update rules are obtained in DID. M…
We consider the problem of minimizing the sum of non-smooth convex functions in non-Euclidean spaces, e.g., probability simplex, via only local computation and communication on an undirected graph. We propose two algorithms motivated by mass-spring-damper dynamics. The first algorithm uses an explicit update that computes subgradients and Bregman projections only, and matches the convergence behavior of centralized mirror descent. The second algorithm uses an implicit update that solves a penalized subproblem at each iteration, and achieves the iteration complexity of \(\mathcal{O}(1/K)\). The…
In this paper, we consider a recursive estimation problem for linear regression where the signal to be estimated admits a sparse representation and measurement samples are only sequentially available. We propose a convergent parallel estimation scheme that consists in solving a sequence of $\ell_{1}$-regularized least-square problems approximately. The proposed scheme is novel in three aspects: i) all elements of the unknown vector variable are updated in parallel at each time instance, and convergence speed is much faster than state-of-the-art schemes which update the elements sequentially; i…
We consider a zeroth-order distributed optimization problem, where the global objective function is a black-box function and, as such, its gradient information is inaccessible to the local agents. Instead, the local agents can only use the values of the objective function to estimate the gradient and update their local decision variables. In this paper, we also assume that these updates are done asynchronously. To solve this problem, we propose an asynchronous zeroth-order distributed optimization method that relies on a one-point residual feedback to estimate the unknown gradient. We show tha…
Distributed Rotary Coverage Control of Multi-Agent Systems in Uncertain Environments
School of Automation, China University of Geosciences（中国地质大学自动化学院）；Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems（复杂系统先进控制与智能自动化湖北省重点实验室）；Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education（教育部地球探测与信息技术工程研究中心）
Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM））；Nokia Bell Labs（诺基亚贝尔实验室）；Sharif University of Technology（谢里夫理工大学）
In this paper, we propose a method of distributed stochastic gradient descent (SGD), with low communication load and computational complexity, and still fast convergence. To reduce the communication load, at each iteration of the algorithm, the worker nodes calculate and communicate some scalers, that are the directional derivatives of the sample functions in some \emph{pre-shared directions}. However, to maintain accuracy, after every specific number of iterations, they communicate the vectors of stochastic gradients. To reduce the computational complexity in each iteration, the worker nodes …
Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration
School of Computer Science and Engineering, Suzhou University of Technology（苏州科技大学计算机科学与工程学院）；School of Mathematics, Southeast University（东南大学数学学院）；School of Cyber Science and Engineering, Southeast University（东南大学网络科学与工程学院）
Tsinghua University（清华大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper proposes a \emph{fully asynchronous} scheme for the policy evaluation problem of distributed reinforcement learning (DisRL) over directed peer-to-peer networks. Without waiting for any other node of the network, each node can locally update its value function at any time by using (possibly delayed) information from its neighbors. This is in sharp contrast to the gossip-based scheme where a pair of nodes concurrently update. Though the fully asynchronous setting involves a difficult multi-timescale decision problem, we design a novel stochastic average gradient (SAG) based distribute…
Rutgers, The State University of New Jersey（罗格斯大学，新泽西州立大学）
We propose new methods to speed up convergence of the Alternating Direction Method of Multipliers (ADMM), a common optimization tool in the context of large scale and distributed learning. The proposed method accelerates the speed of convergence by automatically deciding the constraint penalty needed for parameter consensus in each iteration. In addition, we also propose an extension of the method that adaptively determines the maximum number of iterations to update the penalty. We show that this approach effectively leads to an adaptive, dynamic network topology underlying the distributed opt…
This paper considers a problem of distributed hypothesis testing and social learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The conditional distributions are known locally at the nodes, but the true parameter/hypothesis is not known. An update rule is analyzed in which nodes first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a "non-Bayesian" linear conse…
Massachusetts Institute of Technology（麻省理工学院）；Carnegie Mellon University（卡内基梅隆大学）
We study distributed stochastic convex optimization under the delayed gradient model where the server nodes perform parameter updates, while the worker nodes compute stochastic gradients. We discuss, analyze, and experiment with a setup motivated by the behavior of real-world distributed computation networks, where the machines are differently slow at different time. Therefore, we allow the parameter updates to be sensitive to the actual delays experienced, rather than to worst-case bounds on the maximum delay. This sensitivity leads to larger stepsizes, that can help gain rapid initial conver…
Facebook AI Research（Facebook人工智能研究院）；McGill University（麦吉尔大学）；University of Edinburgh（爱丁堡大学）
Distributed data-parallel algorithms aim to accelerate the training of deep neural networks by parallelizing the computation of large mini-batch gradient updates across multiple nodes. Approaches that synchronize nodes using exact distributed averaging (e.g., via AllReduce) are sensitive to stragglers and communication delays. The PushSum gossip algorithm is robust to these issues, but only performs approximate distributed averaging. This paper studies Stochastic Gradient Push (SGP), which combines PushSum with stochastic gradient updates. We prove that SGP converges to a stationary point of s…
We consider distributed optimization where $N$ nodes in a connected network minimize the sum of their local costs subject to a common constraint set. We propose a distributed projected gradient method where each node, at each iteration $k$, performs an update (is active) with probability $p_k$, and stays idle (is inactive) with probability $1-p_k$. Whenever active, each node performs an update by weight-averaging its solution estimate with the estimates of its active neighbors, taking a negative gradient step with respect to its local cost, and performing a projection onto the constraint set; …
