中文
相关论文

相关论文: Dynamic Regret for Strongly Adaptive Methods and O…

200 篇论文

The performance of online convex optimization algorithms in a dynamic environment is often expressed in terms of the dynamic regret, which measures the decision maker's performance against a sequence of time-varying comparators. In the…

机器学习 · 计算机科学 2022-02-28 Nima Eshraghi , Ben Liang

This paper addresses safe distributed online optimization over an unknown set of linear safety constraints. A network of agents aims at jointly minimizing a global, time-varying function, which is only partially observable to each…

最优化与控制 · 数学 2023-02-27 Ting-Jui Chang , Sapana Chaudhary , Dileep Kalathil , Shahin Shahrampour

In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a stochastic gradient of its own objective function in the previous time, and can communicate with its neighbors via a…

最优化与控制 · 数学 2024-01-29 Yuchen Yang , Kaihong Lu , Long Wang

In this paper we propose a framework for solving constrained online convex optimization problem. Our motivation stems from the observation that most algorithms proposed for online convex optimization require a projection onto the convex set…

机器学习 · 计算机科学 2012-10-01 Mehrdad Mahdavi , Rong Jin , Tianbao Yang

To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms…

机器学习 · 计算机科学 2021-05-17 Lijun Zhang , Guanghui Wang , Wei-Wei Tu , Zhi-Hua Zhou

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

Some of the most compelling applications of online convex optimization, including online prediction and classification, are unconstrained: the natural feasible set is R^n. Existing algorithms fail to achieve sub-linear regret in this…

机器学习 · 计算机科学 2012-11-13 Matthew Streeter , H. Brendan McMahan

We consider Constrained Online Convex Optimization (COCO) with adversarially chosen constraints. At each round, the learner chooses an action before observing the loss and constraint function for that round. The goal is to achieve small…

机器学习 · 计算机科学 2026-05-21 Dhruv Sarkar , Abhishek Sinha

We study online regression with the square loss in a reproducing kernel Hilbert space under a dynamic regret criterion. The learner is compared with a time-varying comparator sequence, and the bounds depend on its path length in the RKHS…

机器学习 · 计算机科学 2026-04-29 Dmitry B. Rokhlin , Georgiy A. Karapetyants

Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of…

机器学习 · 计算机科学 2022-06-09 Sarah Sachs , Hédi Hadiji , Tim van Erven , Cristóbal Guzmán

This paper studies the online optimal control problem with time-varying convex stage costs for a time-invariant linear dynamical system, where a finite lookahead window of accurate predictions of the stage costs are available at each time.…

最优化与控制 · 数学 2019-10-23 Yingying Li , Xin Chen , Na Li

We consider the problem of minimizing different notions of swap regret in online optimization. These forms of regret are tightly connected to correlated equilibrium concepts in games, and have been more recently shown to guarantee…

机器学习 · 计算机科学 2026-05-22 Ioannis Anagnostides , Gabriele Farina , Maxwell Fishelson , Haipeng Luo , Jon Schneider

We consider the problem of universal dynamic regret minimization under exp-concave and smooth losses. We show that appropriately designed Strongly Adaptive algorithms achieve a dynamic regret of $\tilde O(d^2 n^{1/5} C_n^{2/5} \vee d^2)$,…

机器学习 · 计算机科学 2023-02-28 Dheeraj Baby , Yu-Xiang Wang

We study the problem of uncertainty quantification via prediction sets, in an online setting where the data distribution may vary arbitrarily over time. Recent work develops online conformal prediction techniques that leverage regret…

机器学习 · 计算机科学 2023-02-16 Aadyot Bhatnagar , Huan Wang , Caiming Xiong , Yu Bai

A constrained version of the online convex optimization (OCO) problem is considered. With slotted time, for each slot, first an action is chosen. Subsequently the loss function and the constraint violation penalty evaluated at the chosen…

机器学习 · 计算机科学 2023-01-25 Rahul Vaze

We consider the problem of online adaptive control of the linear quadratic regulator, where the true system parameters are unknown. We prove new upper and lower bounds demonstrating that the optimal regret scales as…

机器学习 · 计算机科学 2023-10-05 Max Simchowitz , Dylan J. Foster

In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions. Existing universal methods are limited in the sense that…

机器学习 · 计算机科学 2019-05-16 Guanghui Wang , Shiyin Lu , Lijun Zhang

In repeated interaction problems with adaptive agents, our objective often requires anticipating and optimizing over the space of possible agent responses. We show that many problems of this form can be cast as instances of online…

机器学习 · 计算机科学 2024-06-28 William Brown , Christos Papadimitriou , Tim Roughgarden

We design learning rate schedules that minimize regret for SGD-based online learning in the presence of a changing data distribution. We fully characterize the optimal learning rate schedule for online linear regression via a novel analysis…

机器学习 · 计算机科学 2024-06-19 Matthew Fahrbach , Adel Javanmard , Vahab Mirrokni , Pratik Worah

We study the problem of adaptive control of the stochastic linear quadratic regulator (LQR) with constraints that must be satisfied at every time step. Prior work on the multidimensional problem has shown $\tilde{O}(T^{2/3})$ regret and…

最优化与控制 · 数学 2026-05-08 Spencer Hutchinson , Nanfei Jiang , Mahnoosh Alizadeh