English
Related papers

Related papers: Meta-Learning Guarantees for Online Receding Horiz…

200 papers

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…

Machine Learning · Computer Science 2020-12-01 Peng Zhao , Yu-Jie Zhang , Lijun Zhang , Zhi-Hua Zhou

This paper presents the first non-asymptotic result showing that a model-free algorithm can achieve a logarithmic cumulative regret for episodic tabular reinforcement learning if there exists a strictly positive sub-optimality gap in the…

Machine Learning · Computer Science 2021-02-24 Kunhe Yang , Lin F. Yang , Simon S. Du

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guaranteeing computational…

Machine Learning · Computer Science 2024-09-25 Woojin Chae , Dabeen Lee

In this paper, we improve the kernel alignment regret bound for online kernel learning in the regime of the Hinge loss function. Previous algorithm achieves a regret of $O((\mathcal{A}_TT\ln{T})^{\frac{1}{4}})$ at a computational complexity…

Machine Learning · Computer Science 2024-03-14 Junfan Li , Shizhong Liao

Existing online learning algorithms for adversarial Markov Decision Processes achieve ${O}(\sqrt{T})$ regret after $T$ rounds of interactions even if the loss functions are chosen arbitrarily by an adversary, with the caveat that the…

Machine Learning · Computer Science 2023-10-27 Tiancheng Jin , Junyan Liu , Chloé Rouyer , William Chang , Chen-Yu Wei , Haipeng Luo

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…

Machine Learning · Computer Science 2022-02-28 Nima Eshraghi , Ben Liang

The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is…

Machine Learning · Statistics 2024-05-06 Sang Bin Moon , Abolfazl Hashemi

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…

Machine Learning · Computer Science 2023-06-19 Duo Cheng , Xingyu Zhou , Bo Ji

Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in…

Machine Learning · Computer Science 2021-03-01 Yining Chen , Haipeng Luo , Tengyu Ma , Chicheng Zhang

Model Predictive Control (MPC) is a widely used technique for managing timevarying systems, supported by extensive theoretical analysis. While theoretical studies employing dynamic regret frameworks have established robust performance…

Systems and Control · Electrical Eng. & Systems 2025-02-20 Nhat M. Nguyen

We consider the problem of online learning with non-convex losses. In terms of feedback, we assume that the learner observes - or otherwise constructs - an inexact model for the loss function encountered at each stage, and we propose a…

Machine Learning · Computer Science 2020-10-19 Amélie Héliou , Matthieu Martin , Panayotis Mertikopoulos , Thibaud Rahier

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…

Optimization and Control · Mathematics 2021-01-11 Chenkai Yu , Guanya Shi , Soon-Jo Chung , Yisong Yue , Adam Wierman

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…

Machine Learning · Computer Science 2021-05-17 Lijun Zhang , Guanghui Wang , Wei-Wei Tu , Zhi-Hua Zhou

In citep{Hazan-2008-extract}, the authors showed that the regret of online linear optimization can be bounded by the total variation of the cost vectors. In this paper, we extend this result to general online convex optimization. We first…

Machine Learning · Computer Science 2012-06-15 Tianbao Yang , Mehrdad Mahdavi , Rong Jin , Shenghuo Zhu

We study continuous-time online learning where data are generated by a diffusion process with unknown coefficients. The learner employs a two-layer neural network, continuously updating its parameters in a non-anticipative manner. The…

Machine Learning · Computer Science 2026-04-14 Erhan Bayraktar , Bingyan Han , Ziqing Zhang

Meta reinforcement learning sets a distribution over a set of tasks on which the agent can train at will, then is asked to learn an optimal policy for any test task efficiently. In this paper, we consider a finite set of tasks modeled…

Machine Learning · Computer Science 2024-06-05 Mirco Mutti , Aviv Tamar

We consider the problem of the Zinkevich (2003)-style dynamic regret minimization in online learning with exp-concave losses. We show that whenever improper learning is allowed, a Strongly Adaptive online learner achieves the dynamic regret…

Machine Learning · Computer Science 2021-07-06 Dheeraj Baby , Yu-Xiang Wang

Adaptive gradient algorithms such as ADAGRAD and its variants have gained popularity in the training of deep neural networks. While many works as for adaptive methods have focused on the static regret as a performance metric to achieve a…

Machine Learning · Computer Science 2022-09-07 Parvin Nazari , Esmaile Khorram

We study Model Predictive Control (MPC) and propose a general analysis pipeline to bound its dynamic regret. The pipeline first requires deriving a perturbation bound for a finite-time optimal control problem. Then, the perturbation bound…

Optimization and Control · Mathematics 2022-10-25 Yiheng Lin , Yang Hu , Guannan Qu , Tongxin Li , Adam Wierman

We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control rewards are absent but volatilities of the state processes depend…

Machine Learning · Computer Science 2025-07-25 Yilie Huang , Yanwei Jia , Xun Yu Zhou