中文
相关论文

相关论文: Delayed Feedback in Online Non-Convex Optimization…

200 篇论文

The regret bound of dynamic online learning algorithms is often expressed in terms of the variation in the function sequence ($V_T$) and/or the path-length of the minimizer sequence after $T$ rounds. For strongly convex and smooth…

机器学习 · 计算机科学 2020-08-17 Ting-Jui Chang , Shahin Shahrampour

We consider distributed online convex optimization problems, where the distributed system consists of various computing units connected through a time-varying communication graph. In each time step, each computing unit selects a constrained…

机器学习 · 计算机科学 2019-12-23 Deming Yuan , Alexandre Proutiere , Guodong Shi

We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states, known as non-stochastic control. We introduce a…

机器学习 · 计算机科学 2020-06-26 Max Simchowitz , Karan Singh , Elad Hazan

We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the loss functions are strongly convex or exp-concave, we…

机器学习 · 计算机科学 2021-11-24 Dheeraj Baby , Hilaf Hasson , Yuyang Wang

In this work, we consider a distributed online convex optimization problem, with time-varying (potentially adversarial) constraints. A set of nodes, jointly aim to minimize a global objective function, which is the sum of local convex…

最优化与控制 · 数学 2021-05-06 Pranay Sharma , Prashant Khanduri , Lixin Shen , Donald J. Bucci , Pramod K. Varshney

We consider the classic problem of online convex optimisation. Whereas the notion of static regret is relevant for stationary problems, the notion of switching regret is more appropriate for non-stationary problems. A switching regret is…

机器学习 · 计算机科学 2025-03-07 Stephen Pasteris , Chris Hicks , Vasilios Mavroudis , Mark Herbster

We consider online optimization with binary decision variables and convex loss functions. We design a new algorithm, binary online gradient descent (bOGD) and bound its expected dynamic regret. We provide a regret bound that holds for any…

最优化与控制 · 数学 2022-01-21 Antoine Lesage-Landry , Joshua A. Taylor , Duncan S. Callaway

This work focuses on dynamic regret of online convex optimization that compares the performance of online learning to a clairvoyant who knows the sequence of loss functions in advance and hence selects the minimizer of the loss function at…

机器学习 · 计算机科学 2016-05-17 Tianbao Yang , Lijun Zhang , Rong Jin , Jinfeng Yi

To cope with changing environments, recent developments in online learning have introduced the concepts of adaptive regret and dynamic regret independently. In this paper, we illustrate an intrinsic connection between these two concepts by…

机器学习 · 计算机科学 2018-06-05 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

This paper considers the distributed online convex optimization problem with time-varying constraints over a network of agents. This is a sequential decision making problem with two sequences of arbitrarily varying convex loss and…

最优化与控制 · 数学 2022-12-29 Xinlei Yi , Xiuxian Li , Tao Yang , Lihua Xie , Tianyou Chai , Karl H. Johansson

In this paper, we consider the problem of distributed online convex optimization, where a network of local agents aim to jointly optimize a convex function over a period of multiple time steps. The agents do not have any information about…

最优化与控制 · 数学 2019-11-13 Yan Zhang , Robert J. Ravier , Michael M. Zavlanos , Vahid Tarokh

We investigate distributed online convex optimization with compressed communication, where $n$ learners connected by a network collaboratively minimize a sequence of global loss functions using only local information and compressed data…

机器学习 · 计算机科学 2026-01-12 Sifan Yang , Wenhao Yang , Wei Jiang , Lijun Zhang

Recent literature has made much progress in understanding \emph{online LQR}: a modern learning-theoretic take on the classical control problem in which a learner attempts to optimally control an unknown linear dynamical system with fully…

机器学习 · 计算机科学 2020-10-06 Max Simchowitz

Recently, several universal methods have been proposed for online convex optimization which can handle convex, strongly convex and exponentially concave cost functions simultaneously. However, most of these algorithms have been designed…

机器学习 · 计算机科学 2023-02-14 Arnold Salas

This paper studies bandit convex optimization in non-stationary environments with two-point feedback, using dynamic regret as the performance measure. We propose an algorithm based on bandit mirror descent that extends naturally to…

最优化与控制 · 数学 2026-05-26 Chang He , Bo Jiang , Shuzhong Zhang

This paper considers the distributed online convex-concave optimization with constraint sets over a multiagent network, in which each agent autonomously generates a series of decision pairs through a designable mechanism to cooperatively…

最优化与控制 · 数学 2025-08-14 Wentao Zhang , Baoyong Zhang , Deming Yuan , Shengyuan Xu , Vincent K. N. Lau

We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time.…

机器学习 · 计算机科学 2019-06-18 Lijun Zhang , Tie-Yan Liu , Zhi-Hua Zhou

This paper considers the distributed online bandit optimization problem with nonconvex loss functions over a time-varying digraph. This problem can be viewed as a repeated game between a group of online players and an adversary. At each…

机器学习 · 计算机科学 2024-09-25 Youqing Hua , Shuai Liu , Yiguang Hong , Karl Henrik Johansson , Guangchen Wang

A novel Follow-the-Perturbed-Leader type algorithm is proposed and analyzed for solving general long-term constrained optimization problems in an online manner, where the target and constraint functions are oblivious adversarially generated…

最优化与控制 · 数学 2025-10-02 Shijie Pan , Jianyu Xu , Wenjie Huang

In online convex optimization, some efficient algorithms have been designed for each of the individual classes of objective functions, e.g., convex, strongly convex, and exp-concave. However, existing regret analyses, including those of…

最优化与控制 · 数学 2024-12-13 Tomoya Kamijima , Shinji Ito