中文
相关论文

相关论文: An Online Learning Analysis of Minimax Adaptive Co…

200 篇论文

We investigate online convex optimization in non-stationary environments and choose the dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible…

机器学习 · 计算机科学 2020-12-01 Peng Zhao , Yu-Jie Zhang , Lijun Zhang , Zhi-Hua Zhou

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

In this paper, we study the role of feedback in online learning with switching costs. It has been shown that the minimax regret is $\widetilde{\Theta}(T^{2/3})$ under bandit feedback and improves to $\widetilde{\Theta}(\sqrt{T})$ under…

机器学习 · 计算机科学 2023-06-19 Duo Cheng , Xingyu Zhou , Bo Ji

We study predictive control in a setting where the dynamics are time-varying and linear, and the costs are time-varying and well-conditioned. At each time step, the controller receives the exact predictions of costs, dynamics, and…

最优化与控制 · 数学 2021-06-22 Yiheng Lin , Yang Hu , Haoyuan Sun , Guanya Shi , Guannan Qu , Adam Wierman

We consider the problem of online learning where the sequence of actions played by the learner must adhere to an unknown safety constraint at every round. The goal is to minimize regret with respect to the best safe action in hindsight…

机器学习 · 计算机科学 2024-03-08 Karthik Sridharan , Seung Won Wilson Yoo

We study the regret of optimal strategies for online convex optimization games. Using von Neumann's minimax theorem, we show that the optimal regret in this adversarial setting is closely related to the behavior of the empirical…

机器学习 · 计算机科学 2009-04-01 Jacob Abernethy , Alekh Agarwal , Peter L. Bartlett , Alexander Rakhlin

In this paper, we propose and analyze a new method for online linear quadratic regulator (LQR) control with a priori unknown time-varying cost matrices. The cost matrices are revealed sequentially with the potential for future values to be…

最优化与控制 · 数学 2023-02-22 Yitian Chen , Timothy L. Molloy , Tyler Summers , Iman Shames

Here and in a companion paper, we consider a simple control problem in which the underlying dynamics depend on a parameter $a$ that is unknown and must be learned. In this paper, we assume that $a$ can be any real number and we do not…

最优化与控制 · 数学 2023-09-20 Jacob Carruth , Maximilian F. Eggl , Charles Fefferman , Clarence W. Rowley

We propose an algorithm based on online convex optimization for controlling discrete-time linear dynamical systems. The algorithm is data-driven, i.e., does not require a model of the system, and is able to handle a priori unknown and…

最优化与控制 · 数学 2022-11-17 Marko Nonhoff , Matthias A. Müller

We address the problem of learning to control an unknown nonlinear dynamical system through sequential interactions. Motivated by high-stakes applications in which mistakes can be catastrophic, such as robotics and healthcare, we study…

机器学习 · 计算机科学 2025-04-14 James Wang , Bruce D. Lee , Ingvar Ziemann , Nikolai Matni

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller…

机器学习 · 计算机科学 2018-05-25 Sarah Dean , Horia Mania , Nikolai Matni , Benjamin Recht , Stephen Tu

In online learning, the dynamic regret metric chooses the reference (optimal) solution that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The…

机器学习 · 计算机科学 2019-09-04 Yawei Zhao , Shuang Qiu , Ji Liu

We address online linear optimization problems when the possible actions of the decision maker are represented by binary vectors. The regret of the decision maker is the difference between her realized loss and the best loss she would have…

机器学习 · 计算机科学 2013-04-02 Jean-Yves Audibert , Sébastien Bubeck , Gábor Lugosi

We study the problem of online learning in predictive control of an unknown linear dynamical system with time varying cost functions which are unknown apriori. Specifically, we study the online learning problem where the control algorithm…

机器学习 · 计算机科学 2022-11-01 Deepan Muthirayan , Jianjun Yuan , Dileep Kalathil , Pramod P. Khargonekar

Follow-the-Regularized-Leader (FTRL) is a powerful framework for various online learning problems. By designing its regularizer and learning rate to be adaptive to past observations, FTRL is known to work adaptively to various properties of…

机器学习 · 计算机科学 2025-02-18 Taira Tsuchiya , Shinji Ito

This paper describes a new online convex optimization method which incorporates a family of candidate dynamical models and establishes novel tracking regret bounds that scale with the comparator's deviation from the best dynamical model in…

机器学习 · 统计学 2013-01-08 Eric C. Hall , Rebecca M. Willett

We study the impact of predictions in online Linear Quadratic Regulator control with both stochastic and adversarial disturbances in the dynamics. In both settings, we characterize the optimal policy and derive tight bounds on the minimum…

最优化与控制 · 数学 2021-01-11 Chenkai Yu , Guanya Shi , Soon-Jo Chung , Yisong Yue , Adam Wierman

We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-then-commit algorithm that learns the model Markov…

机器学习 · 计算机科学 2020-03-10 Sahin Lale , Kamyar Azizzadenesheli , Babak Hassibi , Anima Anandkumar

This paper derives an optimal control strategy for a simple stochastic dynamical system with constant drift and an additive control input. Motivated by the example of a physical system with an unexpected change in its dynamics, we take the…

最优化与控制 · 数学 2022-02-09 Daniel Gurevich , Debdipta Goswami , Charles L. Fefferman , Clarence W. Rowley

Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a…

机器学习 · 计算机科学 2017-09-12 Pooria Joulani , András György , Csaba Szepesvári