English
Related papers

Related papers: Demystifying the unreasonable effectiveness of onl…

200 papers

We study unconstrained Online Linear Optimization with Lipschitz losses. Motivated by the pursuit of instance optimality, we propose a new algorithm that simultaneously achieves ($i$) the AdaGrad-style second order gradient adaptivity; and…

Machine Learning · Computer Science 2024-02-23 Zhiyu Zhang , Heng Yang , Ashok Cutkosky , Ioannis Ch. Paschalidis

The trade-off between regret and computational cost is a fundamental problem for online kernel regression, and previous algorithms worked on the trade-off can not keep optimal regret bounds at a sublinear computational complexity. In this…

Machine Learning · Computer Science 2023-06-16 Junfan Li , Shizhong Liao

We develop an online learning algorithm for identifying unlabeled data points that are most informative for training (i.e., active learning). By formulating the active learning problem as the prediction with sleeping experts problem, we…

Machine Learning · Computer Science 2022-02-24 Cenk Baykal , Lucas Liebenwein , Dan Feldman , Daniela Rus

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the…

Machine Learning · Computer Science 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

We address the problem of simultaneously learning and control in an online receding horizon control setting. We consider the control of an unknown linear dynamical system with general cost functions and affine constraints on the control…

Optimization and Control · Mathematics 2022-11-02 Deepan Muthirayan , Jianjun Yuan , Pramod P. Khargonekar

In online convex optimization (OCO), Lipschitz continuity of the functions is commonly assumed in order to obtain sublinear regret. Moreover, many algorithms have only logarithmic regret when these functions are also strongly convex.…

Machine Learning · Computer Science 2021-01-01 Yihan Zhou , Victor S. Portella , Mark Schmidt , Nicholas J. A. Harvey

Motivated by online decision-making in time-varying combinatorial environments, we study the problem of transforming offline algorithms to their online counterparts. We focus on offline combinatorial problems that are amenable to a constant…

Machine Learning · Computer Science 2023-02-07 Rad Niazadeh , Negin Golrezaei , Joshua Wang , Fransisca Susan , Ashwinkumar Badanidiyuru

We develop a reduction-based framework for online learning with delayed feedback that recovers and improves upon existing results for both first-order and bandit convex optimization. Our approach introduces a continuous-time model under…

Machine Learning · Computer Science 2026-02-04 Alexander Ryabchenko , Idan Attias , Daniel M. Roy

This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in…

Machine Learning · Computer Science 2024-05-02 Wei Xiong , Hanze Dong , Chenlu Ye , Ziqi Wang , Han Zhong , Heng Ji , Nan Jiang , Tong Zhang

We study fast rates of convergence in the setting of nonparametric online regression, namely where regret is defined with respect to an arbitrary function class which has bounded complexity. Our contributions are two-fold: - In the…

Machine Learning · Computer Science 2022-04-13 Constantinos Daskalakis , Noah Golowich

Policy Optimization (PO) methods are among the most popular Reinforcement Learning (RL) algorithms in practice. Recently, Sherman et al. [2023a] proposed a PO-based algorithm with rate-optimal regret guarantees under the linear Markov…

Machine Learning · Computer Science 2024-07-04 Asaf Cassel , Aviv Rosenberg

We consider a family of learning strategies for online optimization problems that evolve in continuous time and we show that they lead to no regret. From a more traditional, discrete-time viewpoint, this continuous-time approach allows us…

Optimization and Control · Mathematics 2014-02-28 Joon Kwon , Panayotis Mertikopoulos

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of…

Machine Learning · Computer Science 2020-06-19 Yonathan Efroni , Lior Shani , Aviv Rosenberg , Shie Mannor

Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: \textbf{reward hacking} and \textbf{stable optimization}. Current solutions independently…

Machine Learning · Computer Science 2026-02-13 Li He , Qiang Qu , He Zhao , Stephen Wan , Dadong Wang , Lina Yao , Tongliang Liu

Online learning in arbitrary, and possibly adversarial, environments has been extensively studied in sequential decision-making, and it is closely connected to equilibrium computation in game theory. Most existing online learning algorithms…

Machine Learning · Computer Science 2026-03-20 Mingyang Liu , Yongshan Chen , Zhiyuan Fan , Gabriele Farina , Asuman Ozdaglar , Kaiqing Zhang

Smoothed online combinatorial optimization considers a learner who repeatedly chooses a combinatorial decision to minimize an unknown changing cost function with a penalty on switching decisions in consecutive rounds. We study smoothed…

Machine Learning · Computer Science 2023-01-18 Kai Wang , Zhao Song , Georgios Theocharous , Sridhar Mahadevan

We show how to take any two parameter-free online learning algorithms with different regret guarantees and obtain a single algorithm whose regret is the minimum of the two base algorithms. Our method is embarrassingly simple: just add the…

Machine Learning · Statistics 2019-02-26 Ashok Cutkosky

Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called…

Machine Learning · Computer Science 2022-04-06 Jonathan Lee , Ching-An Cheng , Ken Goldberg , Byron Boots

A natural goal when designing online learning algorithms for non-stationary environments is to bound the regret of the algorithm in terms of the temporal variation of the input sequence. Intuitively, when the variation is small, it should…

Machine Learning · Computer Science 2021-12-08 Gautam Goel , Babak Hassibi

Online linear programming plays an important role in both revenue management and resource allocation, and recent research has focused on developing efficient first-order online learning algorithms. Despite the empirical success of…

Machine Learning · Statistics 2025-01-07 Wenzhi Gao , Dongdong Ge , Chenyu Xue , Chunlin Sun , Yinyu Ye