English
Related papers

Related papers: Online Learning with Cumulative Oversampling: Appl…

200 papers

We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…

Robotics · Computer Science 2026-05-07 Fang Nan , Hao Ma , Qinghua Guan , Josie Hughes , Michael Muehlebach , Marco Hutter

A contextual bandit is a popular framework for online learning to act under uncertainty. In practice, the number of actions is huge and their expected rewards are correlated. In this work, we introduce a general framework for capturing such…

Machine Learning · Computer Science 2023-03-07 Imad Aouali , Branislav Kveton , Sumeet Katariya

In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit…

Computation and Language · Computer Science 2025-06-03 Junjie Zhang , Rushuai Yang , Shunyu Liu , Ting-En Lin , Fei Huang , Yi Chen , Yongbin Li , Dacheng Tao

Online convex optimization (OCO) is a widely used framework in online learning. In each round, the learner chooses a decision in a convex set and an adversary chooses a convex loss function, and then the learner suffers the loss associated…

Machine Learning · Computer Science 2024-04-02 Raunak Kumar , Sarah Dean , Robert Kleinberg

This paper considers online convex optimization (OCO) problems - the paramount framework for online learning algorithm design. The loss function of learning task in OCO setting is based on streaming data so that OCO is a powerful tool to…

Machine Learning · Computer Science 2019-11-26 Wenye Ma

Existing risk-aware multi-armed bandit models typically focus on risk measures of individual options such as variance. As a result, they cannot be directly applied to important real-world online decision making problems with correlated…

Machine Learning · Computer Science 2023-05-12 Yihan Du , Siwei Wang , Zhixuan Fang , Longbo Huang

The combinatorial multi-armed bandit (CMAB) is a cornerstone of sequential decision-making framework, dominated by two algorithmic families: UCB-based and adversarial methods such as follow the regularized leader (FTRL) and online mirror…

Machine Learning · Computer Science 2025-12-30 Zichun Ye , Runqi Wang , Xutong Liu , Shuai Li

We study the budget allocation problem in online marketing campaigns that utilize previously collected offline data. We first discuss the long-term effect of optimizing marketing budget allocation decisions in the offline setting. To…

Machine Learning · Computer Science 2023-09-07 Tianchi Cai , Jiyan Jiang , Wenpeng Zhang , Shiji Zhou , Xierui Song , Li Yu , Lihong Gu , Xiaodong Zeng , Jinjie Gu , Guannan Zhang

Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible…

Machine Learning · Statistics 2018-06-07 Zalán Borsos , Andreas Krause , Kfir Y. Levy

Contextual bandits (CB) are online sequential decision-making problems under partial feedback that underpin many adaptive services. There is a growing demand to deploy CB agents directly on-device, under strict constraints on memory,…

Machine Learning · Computer Science 2026-05-14 Marco Angioli , Kevin Johansson , Antonello Rosato , Amy Loutfi , Denis Kleyko

A matching platform is a system that matches different types of participants, such as companies and job-seekers. In such a platform, merely maximizing the number of matches can result in matches being concentrated on highly popular…

Machine Learning · Computer Science 2026-03-10 Yuki Shibukawa , Koichi Tanaka , Yuta Saito , Shinji Ito

This paper presents a new method for combining (or aggregating or ensembling) multivariate probabilistic forecasts, considering dependencies between quantiles and marginals through a smoothing procedure that allows for online learning. We…

Machine Learning · Statistics 2024-02-08 Jonathan Berrisch , Florian Ziel

In Causal Bayesian Optimization (CBO), an agent intervenes on an unknown structural causal model to maximize a downstream reward variable. In this paper, we consider the generalization where other agents or external events also intervene on…

Machine Learning · Computer Science 2023-08-02 Scott Sussex , Pier Giuseppe Sessa , Anastasiia Makarova , Andreas Krause

Semi-online algorithms that are allowed to perform a bounded amount of repacking achieve guaranteed good worst-case behaviour in a more realistic setting. Most of the previous works focused on minimization problems that aim to minimize some…

Data Structures and Algorithms · Computer Science 2021-04-21 Sebastian Berndt , Kilian Grage , Klaus Jansen , Lukas Johannsen , Maria Kosche

We present algorithms for reducing the Dueling Bandits problem to the conventional (stochastic) Multi-Armed Bandits problem. The Dueling Bandits problem is an online model of learning with ordinal feedback of the form "A is preferred to B"…

Machine Learning · Computer Science 2014-05-15 Nir Ailon , Thorsten Joachims , Zohar Karnin

The deployment of Multi-Armed Bandits (MAB) has become commonplace in many economic applications. However, regret guarantees for even state-of-the-art linear bandit algorithms (such as Optimism in the Face of Uncertainty Linear bandit…

Econometrics · Economics 2023-02-28 Jingwen Zhang , Yifang Chen , Amandeep Singh

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Machine Learning · Computer Science 2019-10-31 Rahaf Aljundi , Lucas Caccia , Eugene Belilovsky , Massimo Caccia , Min Lin , Laurent Charlin , Tinne Tuytelaars

Online-learning literature has focused on designing algorithms that ensure sub-linear growth of the cumulative long-term constraint violations. The drawback of this guarantee is that strictly feasible actions may cancel out constraint…

Optimization and Control · Mathematics 2019-10-22 Ezra Tampubolon , Holger Boche

Reinforcement learning with outcome-based feedback faces a fundamental challenge: when rewards are only observed at trajectory endpoints, how do we assign credit to the right actions? This paper provides the first comprehensive analysis of…

Machine Learning · Computer Science 2025-07-25 Fan Chen , Zeyu Jia , Alexander Rakhlin , Tengyang Xie

Bandit algorithms sequentially accumulate data using adaptive sampling policies, offering flexibility for real-world applications. However, excessive sampling can be costly, motivating the devolopment of early stopping methods and reliable…

Statistics Theory · Mathematics 2025-02-06 Zihan Cui