English
Related papers

Related papers: PAC-Bayes Meets Online Contextual Optimization

200 papers

In this paper, we investigate the framework of Online Convex Optimization (OCO) for online learning. OCO offers a very powerful online learning framework for many applications. In this context, we study a specific framework of OCO called…

Machine Learning · Computer Science 2022-11-01 Deepan Muthirayan , Jianjun Yuan , Pramod P. Khargonekar

We develop a general theory to optimize the frequentist regret for sequential learning problems, where efficient bandit and reinforcement learning algorithms can be derived from unified Bayesian principles. We propose a novel optimization…

Machine Learning · Computer Science 2024-02-12 Yunbei Xu , Assaf Zeevi

Model selection in supervised learning provides costless guarantees as if the model that best balances bias and variance was known a priori. We study the feasibility of similar guarantees for cumulative regret minimization in the stochastic…

Machine Learning · Computer Science 2023-10-25 Sanath Kumar Krishnamurthy , Adrienne Margaret Propp , Susan Athey

We study linear contextual bandits with access to a large, confounded, offline dataset that was sampled from some fixed policy. We show that this problem is closely related to a variant of the bandit problem with side information. We…

Machine Learning · Computer Science 2021-08-11 Guy Tennenholtz , Uri Shalit , Shie Mannor , Yonathan Efroni

Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we…

Machine Learning · Computer Science 2024-06-03 Hao Hu , Yiqin Yang , Jianing Ye , Chengjie Wu , Ziqing Mai , Yujing Hu , Tangjie Lv , Changjie Fan , Qianchuan Zhao , Chongjie Zhang

Bayesian learning is a powerful learning framework which combines the external information of the data (background information) with the internal information (training data) in a logically consistent way in inference and prediction. By…

Machine Learning · Statistics 2026-02-11 Erdong Guo , David Draper

We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential…

Machine Learning · Computer Science 2019-12-10 Mikhail Khodak , Maria-Florina Balcan , Ameet Talwalkar

In this paper, we consider the contextual variant of the MNL-Bandit problem. More specifically, we consider a dynamic set optimization problem, where a decision-maker offers a subset (assortment) of products to a consumer and observes the…

Machine Learning · Computer Science 2024-04-16 Priyank Agrawal , Theja Tulabandhula , Vashist Avadhanula

We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial…

Machine Learning · Computer Science 2015-06-15 Alexander Rakhlin , Karthik Sridharan

Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open…

Machine Learning · Computer Science 2026-02-09 Chase Hutton , Adam Melrod , Han Shao

We give an oracle-based algorithm for the adversarial contextual bandit problem, where either contexts are drawn i.i.d. or the sequence of contexts is known a priori, but where the losses are picked adversarially. Our algorithm is…

Machine Learning · Computer Science 2016-06-02 Vasilis Syrgkanis , Haipeng Luo , Akshay Krishnamurthy , Robert E. Schapire

We focus on a stochastic learning model where the learner observes a finite set of training examples and the output of the learning process is a data-dependent distribution over a space of hypotheses. The learned data-dependent distribution…

Machine Learning · Statistics 2020-12-29 Omar Rivasplata , Ilja Kuzborskij , Csaba Szepesvari , John Shawe-Taylor

Background: Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the data distribution during learning. This phenomenon has long been considered a major obstacle for using learning agents in realistic…

Machine Learning · Statistics 2021-10-19 Chen Zeno , Itay Golan , Elad Hoffer , Daniel Soudry

We study nonparametric contextual bandits under batch constraints, where the expected reward for each action is modeled as a smooth function of covariates, and the policy updates are made at the end of each batch of observations. We…

Statistics Theory · Mathematics 2025-10-06 Rong Jiang , Cong Ma

Predicting the output of a dynamical system from streaming data is fundamental to real-time feedback control and decision-making. We first derive an autoregressive representation that relates future local outputs to asynchronous past…

Systems and Control · Electrical Eng. & Systems 2026-03-09 Jiachen Qian , Yang Zheng

Contextual bandits are widely used in industrial personalization systems. These online learning frameworks learn a treatment assignment policy in the presence of treatment effects that vary with the observed contextual features of the…

Machine Learning · Computer Science 2022-05-11 Claudia Roberts , Maria Dimakopoulou , Qifeng Qiao , Ashok Chandrashekhar , Tony Jebara

A key component of cognitive radar is the ability to generalize, or achieve consistent performance across a range of sensing environments, since aspects of the physical scene may vary over time. This presents a challenge for learning-based…

Information Theory · Computer Science 2023-02-08 Charles E. Thornton , R. Michael Buehrer , Anthony F. Martone

PAC-Bayes learning is a comprehensive setting for (i) studying the generalisation ability of learning algorithms and (ii) deriving new learning algorithms by optimising a generalisation bound. However, optimising generalisation bounds might…

Machine Learning · Statistics 2024-11-27 Antoine Picard-Weibel , Roman Moscoviz , Benjamin Guedj

We consider a PAC-Bayes type learning rule for binary classification, balancing the training error of a randomized ''posterior'' predictor with its KL divergence to a pre-specified ''prior''. This can be seen as an extension of a modified…

Machine Learning · Statistics 2026-03-25 Xiaohan Zhu , Mesrob I. Ohannessian , Nathan Srebro

Time-varying systems are a challenge in many scientific and engineering areas. Usually, estimation of time-varying parameters or signals must be performed online, which calls for the development of responsive online algorithms. In this…

Optimization and Control · Mathematics 2018-09-10 Sophie M. Fosson