English
Related papers

Related papers: On the relation between dynamic regret and closed-…

200 papers

Optimization under uncertainty and risk is indispensable in many practical situations. Our paper addresses stability of optimization problems using composite risk functionals which are subjected to measure perturbations. Our main focus is…

Optimization and Control · Mathematics 2022-01-06 Darinka Dentcheva , Yang Lin , Spiridon Penev

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…

Machine Learning · Computer Science 2020-06-26 Max Simchowitz , Karan Singh , Elad Hazan

Recently, there has been a growing research interest in the analysis of dynamic regret, which measures the performance of an online learner against a sequence of local minimizers. By exploiting the strong convexity, previous studies have…

Machine Learning · Computer Science 2017-11-03 Lijun Zhang , Tianbao Yang , Jinfeng Yi , Rong Jin , Zhi-Hua Zhou

A sufficient condition for the stability of a system resulting from the interconnection of dynamical systems is given by the small gain theorem. Roughly speaking, to apply this theorem, it is required that the gains composition is…

Dynamical Systems · Mathematics 2015-08-12 Humberto Stein Shiromoto , Vincent Andrieu , Christophe Prieur

We study the performance of asymptotic and approximate consensus algorithms under harsh environmental conditions. The asymptotic consensus problem requires a set of agents to repeatedly set their outputs such that the outputs converge to a…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-06-28 Matthias Függer , Thomas Nowak , Manfred Schwarz

In learning theory, the performance of an online policy is commonly measured in terms of the static regret metric, which compares the cumulative loss of an online policy to that of an optimal benchmark in hindsight. In the definition of…

Information Theory · Computer Science 2022-08-23 Ativ Joshi , Abhishek Sinha

Past research on interactive decision making problems (bandits, reinforcement learning, etc.) mostly focuses on the minimax regret that measures the algorithm's performance on the hardest instance. However, an ideal algorithm should adapt…

Machine Learning · Computer Science 2023-06-13 Kefan Dong , Tengyu Ma

Dynamic pricing of goods in a competitive environment to maximize revenue is a natural objective and has been a subject of research over the years. In this paper, we focus on a class of markets exhibiting the substitutes property with…

Machine Learning · Computer Science 2017-09-18 Paresh Nakhe

This paper addresses the problem of stabilization for infinite-dimensional systems. In particular, we design nonlinear stabilizers for both linear and nonlinear abstract systems. We focus on two classes of systems: the first class comprises…

Systems and Control · Electrical Eng. & Systems 2025-09-19 Kamal Fenza , Moussa Labbadi , Mohamed Ouzahra

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

Machine Learning · Computer Science 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

We present an online learning analysis of minimax adaptive control for the case where the uncertainty includes a finite set of linear dynamical systems. Precisely, for each system inside the uncertainty set, we define the model-based regret…

Systems and Control · Electrical Eng. & Systems 2023-09-12 Venkatraman Renganathan , Andrea Iannelli , Anders Rantzer

The paper endeavours to solve the problem of the necessary and sufficient conditions for testing asymptotic stability of the equilibrium state without using a positive definite or semi-definite Lyapunov function for time-invariant nonlinear…

Dynamical Systems · Mathematics 2017-11-07 Rachid Bouyekhf , Lyubomir T. Gruyitch

Steady state fluctuation relations for dynamical systems are commonly derived under the assumption of some form of time-reversibility and of chaos. There are, however, cases in which they are observed to hold even if the usual notion of…

Mathematical Physics · Physics 2015-05-27 Matteo Colangeli , Rainer Klages , Paolo De Gregorio , Lamberto Rondoni

We analyze stability properties of monotone nonlinear systems via max-separable Lyapunov functions, motivated by the following observations: first, recent results have shown that asymptotic stability of a monotone nonlinear system implies…

Systems and Control · Computer Science 2016-07-28 Hamid Reza Feyzmahdavian , Bart Besselink , Mikael Johansson

Recent results in the literature have provided connections between the so-called turnpike property, near optimality of closed-loop solutions, and strict dissipativity. Motivated by applications in economics, optimal control problems with…

Optimization and Control · Mathematics 2022-02-18 Lars Grüne , Lisa Krügel

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2023-09-28 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

The stability of linear dynamic systems with hysteresis in feedback is considered. While the absolute stability for memoryless nonlinearities (known as Lure's problem) can be proved by the well-known circle criterion, the multivalued…

Systems and Control · Electrical Eng. & Systems 2020-02-11 Michael Ruderman

We study non-convex delayed-noise online optimization problems by evaluating dynamic regret in the non-stationary setting when the loss functions are quasar-convex. In particular, we consider scenarios involving quasar-convex functions…

Optimization and Control · Mathematics 2026-01-08 Felipe Lara , Cristian Vega

Standard dynamical systems theory is centred around the coordinate-invariant asymptotic-time properties of autonomous systems. We identify three limitations of this approach. Firstly, we discuss how the traditional approach cannot take into…

Adaptation and Self-Organizing Systems · Physics 2018-10-10 Julian Newman , Maxime Lucas , Aneta Stefanovska

This paper is concerned with the asymptotic stability analysis of a one dimensional wave equation subject to a nonmonotone distributed damping. A well-posedness result is provided together with a precise characterization of the asymptotic…

Analysis of PDEs · Mathematics 2019-02-07 Swann Marx , Yacine Chitour , Christophe Prieur