English
Related papers

Related papers: Demystifying the unreasonable effectiveness of onl…

200 papers

Gradient-variation online learning aims to achieve regret guarantees that scale with variations in the gradients of online functions, which has been shown to be crucial for attaining fast convergence in games and robustness in stochastic…

Machine Learning · Computer Science 2024-11-05 Yan-Feng Xie , Peng Zhao , Zhi-Hua Zhou

Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistical efficiency have not been formally established. This paper characterizes the conditions…

Machine Learning · Computer Science 2026-05-12 Enoch Hyunwook Kang

We study the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to depend on past decisions and thus captures temporal effects of learning problems. In this paper, we introduce dynamic policy regret as the…

Machine Learning · Computer Science 2023-08-16 Peng Zhao , Yu-Hu Yan , Yu-Xiang Wang , Zhi-Hua Zhou

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…

Machine Learning · Computer Science 2017-09-12 Pooria Joulani , András György , Csaba Szepesvári

We study computationally and statistically efficient reinforcement learning under the linear $Q^{\pi}$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this…

Machine Learning · Computer Science 2026-03-03 Yijing Ke , Zihan Zhang , Ruosong Wang

Inspired by the demands of real-time climate and weather forecasting, we develop optimistic online learning algorithms that require no parameter tuning and have optimal regret guarantees under delayed feedback. Our algorithms -- DORM,…

Most of the existing works for reinforcement learning (RL) with general function approximation (FA) focus on understanding the statistical complexity or regret bounds. However, the computation complexity of such approaches is far from being…

Machine Learning · Computer Science 2023-04-19 Dingwen Kong , Ruslan Salakhutdinov , Ruosong Wang , Lin F. Yang

Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls to planning and statistical estimation oracles. While…

Machine Learning · Computer Science 2026-05-04 Haichen Hu , Jian Qian , David Simchi-Levi

Combinatorial multi-armed bandits provide a fundamental online decision-making environment where a decision-maker interacts with an environment across $T$ time steps, each time selecting an action and learning the cost of that action. The…

Machine Learning · Computer Science 2026-04-13 Gerdus Benadè , Rathish Das , Thomas Lavastida

In this paper, we improve the regret bound for online kernel selection under bandit feedback. Previous algorithm enjoys a $O((\Vert f\Vert^2_{\mathcal{H}_i}+1)K^{\frac{1}{3}}T^{\frac{2}{3}})$ expected bound for Lipschitz loss functions. We…

Machine Learning · Computer Science 2023-03-24 Junfan Li , Shizhong Liao

We study an online linear regression setting in which the observed feature vectors are corrupted by noise and the learner can pay to reduce the noise level. In practice, this may happen for several reasons: for example, because features can…

Machine Learning · Computer Science 2025-11-12 Nadav Merlis , Kyoungseok Jang , Nicolò Cesa-Bianchi

We present a new online learning algorithm for cumulative discounted gain. This learning algorithm does not use exponential weights on the experts. Instead, it uses a weighting scheme that depends on the regret of the master algorithm…

Computer Science and Game Theory · Computer Science 2008-07-01 Yoav Freund , Daniel Hsu

We consider the setting of online logistic regression and consider the regret with respect to the 2-ball of radius B. It is known (see [Hazan et al., 2014]) that any proper algorithm which has logarithmic regret in the number of samples…

Machine Learning · Computer Science 2020-11-04 Rémi Jézéquel , Pierre Gaillard , Alessandro Rudi

Regret has been widely adopted as the metric of choice for evaluating the performance of online optimization algorithms for distributed, multi-agent systems. However, data/model variations associated with agents can significantly impact…

Machine Learning · Computer Science 2022-09-22 Zhanhong Jiang , Aditya Balu , Xian Yeow Lee , Young M. Lee , Chinmay Hegde , Soumik Sarkar

We study an online linear programming (OLP) problem under a random input model in which the columns of the constraint matrix along with the corresponding coefficients in the objective function are generated i.i.d. from an unknown…

Data Structures and Algorithms · Computer Science 2021-04-20 Xiaocheng Li , Yinyu Ye

We consider the problem of online learning in Linear Quadratic Control systems whose state transition and state-action transition matrices $A$ and $B$ may be initially unknown. We devise an online learning algorithm and provide guarantees…

Machine Learning · Computer Science 2021-09-30 Yassir Jedra , Alexandre Proutiere

We study dynamic regret in online convex optimization, where the objective is to achieve low cumulative loss relative to an arbitrary benchmark sequence. By observing that competing with an arbitrary sequence of comparators…

Machine Learning · Computer Science 2025-12-12 Andrew Jacobsen , Alessandro Rudi , Francesco Orabona , Nicolo Cesa-Bianchi

Practical online learning tasks are often naturally defined on unconstrained domains, where optimal algorithms for general convex losses are characterized by the notion of comparator adaptivity. In this paper, we design such algorithms in…

Machine Learning · Computer Science 2022-10-13 Zhiyu Zhang , Ashok Cutkosky , Ioannis Ch. Paschalidis

We study a variant of online optimization in which the learner receives $k$-round $\textit{delayed feedback}$ about hitting cost and there is a multi-step nonlinear switching cost, i.e., costs depend on multiple previous actions in a…

Machine Learning · Computer Science 2021-11-02 Weici Pan , Guanya Shi , Yiheng Lin , Adam Wierman

Motivated by real-world settings where data collection and policy deployment -- whether for a single agent or across multiple agents -- are costly, we study the problem of on-policy single-agent reinforcement learning (RL) and federated RL…

Machine Learning · Statistics 2026-03-11 Haochen Zhang , Zhong Zheng , Lingzhou Xue