arXiv subjects

Xiuxian Li

Publications and source records attributed to Xiuxian Li.

35 records · Page 2Linked to original sources

arXiv2021

On Faster Convergence of Scaled Sign Gradient Descent

Communication has been seen as a significant bottleneck in industrial applications over large-scale networks. To alleviate the communication burden, sign-based optimization algorithms have gained popularity recently in both industrial and academic communities, which is shown to be closely related to adaptive gradient methods, such as Adam. Along this line, this paper investigates faster convergence for a variant of sign-based gradient descent, called scaled signGD, in three cases: 1) the objective function is strongly convex; 2) the objective function is nonconvex but satisfies the Polyak-Lojasiewicz (PL) inequality; 3) the gradient is stochastic, called scaled signGD in this case. For the first two cases, it can be shown that the scaled signGD converges at a linear rate. For case 3), the algorithm is shown to converge linearly to a neighborhood of the optimal value when a constant learning rate is employed, and the algorithm converges at a rate of $O(1/k)$ when using a diminishing learning rate, where $k$ is the iteration number. The results are also extended to the distributed setting by majority vote in a parameter-server framework. Finally, numerical experiments on logistic regression are performed to corroborate the theoretical findings.

math.OC↗

arXiv2021

DOT and DOP: Linearly Convergent Algorithms for Finding Fixed Points of Multi-Agent Operators

This paper investigates the distributed fixed point finding problem for a global operator over a directed and unbalanced multi-agent network, where the global operator is quasinonexpansive and only partially accessible to each individual agent. Two cases are addressed, that is, the global operator is sum separable and block separable. For this first case, the global operator is the sum of local operators, which are assumed to be Lipschitz, and each local operator is privately known to each individual agent. To deal with this scenario, a distributed (or decentralized) algorithm, called Distributed quasi-averaged Operator Tracking algorithm (DOT), is proposed and rigorously analyzed, and it is shown that the algorithm can converge to a fixed point of the global operator at a linear rate under a linear regularity condition, which is strictly weaker than the strong convexity assumption on cost functions in existing convex optimization literature. For the second scenario, the global operator is composed of a group of local block operators which are Lipschitz and can be accessed only by each individual agent. In this setup, a distributed algorithm, called Distributed quasiaveraged Operator Playing algorithm (DOP), is developed and shown to be linearly convergent to a fixed point of the global operator under the linear regularity condition. The above studied problems provide a unified framework for many interesting problems. As examples, the proposed DOT and DOP are exploited to deal with distributed optimization and multi-player games under partial-decision information. Finally, numerical examples are presented to corroborate the theoretical results.

math.OC↗

arXiv2021

Online Abstract Dynamic Programming with Contractive Models

This paper addresses the abstract dynamic programming (DP) in the online scenario, where the abstract DP mapping is time-varying, instead of static. In this case, optimal costs and policies at different time instants are not the same in general, and the problem amounts to tracking time-varying optimal costs and policies, which is of interest to many practical problems. It is thus necessary to analyze the performance of classical value iteration (VI) and policy iteration (PI) algorithms in the online case. In doing so, this paper develops and provides the theoretical analysis for several online algorithms, including approximate online VI, online PI, approximate online PI, online optimistic PI, approximate online optimistic PI, and asynchronous online PI and VI algorithms. It is proved that the tracking error bounds for all algorithms critically depend upon the largest difference between any two consecutive abstract mappings. Meanwhile, examples are presented to illustrate the theoretical results.

math.OC↗

arXiv2021

Composition and Application of Current Advanced Driving Assistance System: A Review

Due to the growing awareness of driving safety and the development of sophisticated technologies, advanced driving assistance system (ADAS) has been equipped in more and more vehicles with higher accuracy and lower price. The latest progress in this field has called for a review to sum up the conventional knowledge of ADAS, the state-of-the-art researches, and novel applications in real-world. With the help of this kind of review, newcomers in this field can get basic knowledge easier and other researchers may be inspired with potential future development possibility. This paper makes a general introduction about ADAS by analyzing its hardware support and computation algorithms. Different types of perception sensors are introduced from their interior feature classifications, installation positions, supporting ADAS functions, and pros and cons. The comparisons between different sensors are concluded and illustrated from their inherent characters and specific usages serving for each ADAS function. The current algorithms for ADAS functions are also collected and briefly presented in this paper from both traditional methods and novel ideas. Additionally, discussions about the definition of ADAS from different institutes are reviewed in this paper, and future approaches about ADAS in China are introduced in particular.

cs.AI↗

arXiv2021

Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints

This paper considers online convex optimization with long term constraints, where constraints can be violated in intermediate rounds, but need to be satisfied in the long run. The cumulative constraint violation is used as the metric to measure constraint violations, which excludes the situation that strictly feasible constraints can compensate the effects of violated constraints. A novel algorithm is first proposed and it achieves an $\mathcal{O}(T^{\max\{c,1-c\}})$ bound for static regret and an $\mathcal{O}(T^{(1-c)/2})$ bound for cumulative constraint violation, where $c\in(0,1)$ is a user-defined trade-off parameter, and thus has improved performance compared with existing results. Both static regret and cumulative constraint violation bounds are reduced to $\mathcal{O}(\log(T))$ when the loss functions are strongly convex, which also improves existing results. %In order to bound the regret with respect to any comparator sequence, In order to achieve the optimal regret with respect to any comparator sequence, another algorithm is then proposed and it achieves the optimal $\mathcal{O}(\sqrt{T(1+P_T)})$ regret and an $\mathcal{O}(\sqrt{T})$ cumulative constraint violation, where $P_T$ is the path-length of the comparator sequence. Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results.

cs.LG↗

arXiv2021

Decentralized Online Learning for Noncooperative Games in Dynamic Environments

Decentralized online learning for seeking generalized Nash equilibrium (GNE) of noncooperative games in dynamic environments is studied in this paper. Each player aims at selfishly minimizing its own time-varying cost function subject to time-varying coupled constraints and local feasible set constraints. Only local cost functions and local constraints are available to individual players, who can receive their neighbors' information through a fixed and connected graph. In addition, players have no prior knowledge of cost functions and local constraint functions in the future time. In this setting, a novel distributed online learning algorithm for seeking GNE of the studied game is devised based on mirror descent and a primal-dual strategy. It is shown that the presented algorithm can achieve sublinearly bounded dynamic regrets and constraint violation by appropriately choosing decreasing stepsizes. Finally, the obtained theoretical result is corroborated by a numerical simulation.

math.OC↗

arXiv2021

Exponential convergence of distributed optimization for heterogeneous linear multi-agent systems

In this work we study a distributed optimal output consensus problem for heterogeneous linear multi-agent systems where the agents aim to reach consensus with the purpose of minimizing the sum of private convex costs. Based on output feedback, a fully distributed control law is proposed by using the proportional-integral (PI) control technique. For strongly convex cost functions with Lipschitz gradients, the designed controller can achieve convergence exponentially in an undirected and connected network. Furthermore, to remove the requirement of continuous communications, the proposed control law is then extended to periodic and event-triggered communication schemes, which also achieve convergence exponentially. Two simulation examples are given to verify the proposed control algorithms.

eess.SY↗

arXiv2020

Aug-PDG: Linear Convergence of Convex Optimization with Inequality Constraints

This paper investigates the convex optimization problem with general convex inequality constraints. To cope with this problem, a discrete-time algorithm, called augmented primal-dual gradient algorithm (Aug-PDG), is studied and analyzed. It is shown that Aug-PDG can converge semi-globally to the optimizer at a linear rate under some mild assumptions, such as the quadratic gradient growth condition for the objective function, which is strictly weaker than strong convexity. To our best knowledge, this paper is the first to establish a linear convergence for the studied problem in the discrete-time setting, where an explicit bound is provided for the stepsize. Finally, a numerical example is presented to illustrate the efficacy of the theoretical finding.

math.OC↗

arXiv2020

Distributed Online Convex Optimization with an Aggregative Variable

This paper investigates distributed online convex optimization in the presence of an aggregative variable without any global/central coordinators over a multi-agent network, where each individual agent is only able to access partial information of time-varying global loss functions, thus requiring local information exchanges between neighboring agents. Motivated by many applications in reality, the considered local loss functions depend not only on their own decision variables, but also on an aggregative variable, such as the average of all decision variables. To handle this problem, an Online Distributed Gradient Tracking algorithm (O-DGT) is proposed with exact gradient information and it is shown that the dynamic regret is upper bounded by three terms: a sublinear term, a path variation term, and a gradient variation term. Meanwhile, the O-DGT algorithm is also analyzed with stochastic/noisy gradients, showing that the expected dynamic regret has the same upper bound as the exact gradient case. To our best knowledge, this paper is the first to study online convex optimization in the presence of an aggregative variable, which enjoys new characteristics in comparison with the conventional scenario without the aggregative variable. Finally, a numerical experiment is provided to corroborate the obtained theoretical results.

math.OC↗

arXiv2020

Distributed Online Optimization for Multi-Agent Networks with Coupled Inequality Constraints

This paper investigates the distributed online optimization problem over a multi-agent network subject to local set constraints and coupled inequality constraints, which has a lot of applications in many areas, such as wireless sensor networks, power systems and plug-in electric vehicles. In this problem, the cost function at each time step is the sum of local cost functions with each of them being gradually revealed to its corresponding agent, and meanwhile only local functions in coupled inequality constraints are accessible to each agent. To address this problem, a modified primal-dual algorithm, called distributed online primal-dual push-sum algorithm (DOPP), is developed in this paper, which does not rest on any assumption on parameter boundedness and is applicable to unbalanced networks. It is shown that the proposed algorithm is sublinear for both the dynamic regret and the violation of coupled inequality constraints. Finally, the theoretical results are supported by a simulation example.

math.OC↗

arXiv2020

Distributed Proximal Algorithms for Multi-Agent Optimization with Coupled Inequality Constraints

This paper aims to address distributed optimization problems over directed and time-varying networks, where the global objective function consists of a sum of locally accessible convex objective functions subject to a feasible set constraint and coupled inequality constraints whose information is only partially accessible to each agent. For this problem, a distributed proximal-based algorithm, called distributed proximal primal-dual (DPPD) algorithm, is proposed based on the celebrated centralized proximal point algorithm. It is shown that the proposed algorithm can lead to the global optimal solution with a general stepsize, which is diminishing and non-summable, but not necessarily square-summable, and the saddle-point running evaluation error vanishes proportionally to $O(1/\sqrt{k})$, where $k>0$ is the iteration number. Finally, a simulation example is presented to corroborate the effectiveness of the proposed algorithm.

math.OC↗

arXiv2020

Distributed Aggregative Optimization over Multi-Agent Networks

This paper proposes a new framework for distributed optimization, called distributed aggregative optimization, which allows local objective functions to be dependent not only on their own decision variables, but also on the average of summable functions of decision variables of all other agents. To handle this problem, a distributed algorithm, called distributed gradient tracking (DGT), is proposed and analyzed, where the global objective function is strongly convex, and the communication graph is balanced and strongly connected. It is shown that the algorithm can converge to the optimal variable at a linear rate. A numerical example is provided to corroborate the theoretical result.

math.OC↗

arXiv2020

A "Safe Kernel" Approach for Resilient Multi-Dimensional Consensus

This paper considers the resilient multi-dimensional consensus problem in networked systems, where some of the agents might be malicious (or faulty). We propose a multi-dimensional consensus algorithm, where at each time step each healthy agent computes a "safe kernel" based on the information from its neighbors, and modifies its own state towards a point inside the kernel. Assuming that the number of malicious agents is locally (or globally) upper bounded, sufficient conditions on the network topology are presented to guarantee that the benign agents exponentially reach an agreement within the convex hull of their initial states, regardless of the actions of the misbehaving ones. It is also revealed that the graph connectivity and robustness required to achieve the resilient consensus increases linearly with respect to the dimension of the agents' state, indicating the existence of a trade-off between the low communication cost and system security. Numerical examples are provided in the end to validate the theoretical results.

eess.SY↗

arXiv2019

Distributed Bandit Online Convex Optimization with Time-Varying Coupled Inequality Constraints

This paper considers the problem of distributed bandit online convex optimization with time-varying coupled inequality constraints. This problem can be defined as a repeated game between a group of learners and an adversary. The learners attempt to minimize a sequence of global loss functions and at the same time satisfy a sequence of coupled constraint functions. The global loss and the coupled constraint functions are the sum of local convex loss and constraint functions, respectively, which are adaptively generated by the adversary. The local loss and constraint functions are revealed in a bandit manner, i.e., only the values of loss and constraint functions at sampled points are revealed to the learners, and the revealed function values are held privately by each learner. We consider two scenarios, one- and two-point bandit feedback, and propose two corresponding distributed bandit online algorithms used by the learners. We show that sublinear expected regret and constraint violation are achieved by these two algorithms, if the accumulated variation of the comparator sequence also grows sublinearly. In particular, we show that $\mathcal{O}(T^{θ_1})$ expected static regret and $\mathcal{O}(T^{7/4-θ_1})$ constraint violation are achieved in the one-point bandit feedback setting, and $\mathcal{O}(T^{\max\{κ,1-κ\}})$ expected static regret and $\mathcal{O}(T^{1-κ/2})$ constraint violation in the two-point bandit feedback setting, where $θ_1\in(3/4,5/6]$ and $κ\in(0,1)$ are user-defined trade-off parameters. Finally, these theoretical results are illustrated by numerical simulations of a simple power grid example.

math.OC↗

arXiv2019

Distributed Algorithms for Computing a Fixed Point of Multi-Agent Nonexpansive Operators

This paper investigates the problem of finding a fixed point for a global nonexpansive operator under time-varying communication graphs in real Hilbert spaces, where the global operator is separable and composed of an aggregate sum of local nonexpansive operators. Each local operator is only privately accessible to each agent, and all agents constitute a network. To seek a fixed point of the global operator, it is indispensable for agents to exchange local information and update their solution cooperatively. To solve the problem, two algorithms are developed, called distributed Krasnosel'ski\uı-Mann (D-KM) and distributed block-coordinate Krasnosel'ski\uı-Mann (D-BKM) iterations, for which the D-BKM iteration is a block-coordinate version of the D-KM iteration in the sense of randomly choosing and computing only one block-coordinate of local operators at each time for each agent. It is shown that the proposed two algorithms can both converge weakly to a fixed point of the global operator. Meanwhile, the designed algorithms are applied to recover the classical distributed gradient descent (DGD) algorithm, devise a new block-coordinate DGD algorithm, handle a distributed shortest distance problem in the Hilbert space for the first time, and solve linear algebraic equations in a novel distributed approach. Finally, the theoretical results are corroborated by a few numerical examples.

math.OC↗

arXiv2019

Distributed Online Convex Optimization with Time-Varying Coupled Inequality Constraints

This paper considers distributed online optimization with time-varying coupled inequality constraints. The global objective function is composed of local convex cost and regularization functions and the coupled constraint function is the sum of local convex functions. A distributed online primal-dual dynamic mirror descent algorithm is proposed to solve this problem, where the local cost, regularization, and constraint functions are held privately and revealed only after each time slot. Without assuming Slater's condition, we first derive regret and constraint violation bounds for the algorithm and show how they depend on the stepsize sequences, the accumulated dynamic variation of the comparator sequence, the number of agents, and the network connectivity. As a result, under some natural decreasing stepsize sequences, we prove that the algorithm achieves sublinear dynamic regret and constraint violation if the accumulated dynamic variation of the optimal sequence also grows sublinearly. We also prove that the algorithm achieves sublinear static regret and constraint violation under mild conditions. Assuming Slater's condition, we show that the algorithm achieves smaller bounds on the constraint violation. In addition, smaller bounds on the static regret are achieved when the objective function is strongly convex. Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results.

math.OC↗

arXiv2019

Distributed Algorithms for Computing a Common Fixed Point of a Group of Nonexpansive Operators

This paper addresses the problem of seeking a common fixed point for a collection of nonexpansive operators over time-varying multi-agent networks in real Hilbert spaces, where each operator is only privately and approximately known to each individual agent, and all agents need to cooperate to solve this problem by propagating their own information to their neighbors through local communications over time-varying networks. To handle this problem, inspired by the centralized inexact Krasnosel'ski\uı-Mann (IKM) iteration, we propose a distributed algorithm, called distributed inexact Krasnosel'ski\uı-Mann (D-IKM) iteration. It is shown that the D-IKM iteration can converge weakly to a common fixed point of the family of nonexpansive operators. Moreover, under the assumption that all operators and their own fixed point sets are (boundedly) linearly regular, it is proved that the D-IKM iteration converges with a rate $O(1/k^{\ln(1/ξ)})$ for some constant $ξ\in(0,1)$, where $k$ is the iteration number. To reduce computational complexity and burden of storage and transmission, a scenario, where only a random part of coordinates for each agent is updated at each iteration, is further considered, and a corresponding algorithm, named distributed inexact block-coordinate Krasnosel'ski\uı-Mann (D-IBKM) iteration, is developed. The algorithm is proved to be weakly convergent to a common fixed point of the group of considered operators, and, with the extra assumption of (bounded) linear regularity, it is convergent with a rate $O(1/k^{\ln(1/ξ)})$. Furthermore, it is shown that the convergence rate $O(1/k^{\ln(1/ξ)})$ can still be guaranteed under a more relaxed (bounded) power regularity condition.

math.OC↗