English
Related papers

Related papers: Online Learning with Off-Policy Feedback

200 papers

Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the loss compared to an…

Machine Learning · Computer Science 2024-02-13 Yuval Filmus , Steve Hanneke , Idan Mehalel , Shay Moran

Is it possible to make online decisions when personalized covariates are unavailable? We take a collaborative-filtering approach for decision-making based on collective preferences. By assuming low-dimensional latent features, we formulate…

Machine Learning · Statistics 2024-12-20 Congyuan Duan , Jingyang Li , Dong Xia

Contextual bandit algorithms are ubiquitous tools for active sequential experimentation in healthcare and the tech industry. They involve online learning algorithms that adaptively learn policies over time to map observed contexts $X_t$ to…

Methodology · Statistics 2024-08-19 Ian Waudby-Smith , Lili Wu , Aaditya Ramdas , Nikos Karampatziakis , Paul Mineiro

The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the…

Machine Learning · Computer Science 2020-03-24 Raman Arora , Michael Dinitz , Teodor V. Marinov , Mehryar Mohri

We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm…

Machine Learning · Computer Science 2011-10-28 Alina Beygelzimer , John Langford , Lihong Li , Lev Reyzin , Robert E. Schapire

We consider the problem of online learning in misspecified linear stochastic multi-armed bandit problems. Regret guarantees for state-of-the-art linear bandit algorithms such as Optimism in the Face of Uncertainty Linear bandit (OFUL) hold…

Machine Learning · Computer Science 2017-04-25 Avishek Ghosh , Sayak Ray Chowdhury , Aditya Gopalan

An adversarial bandit problem with memory constraints is studied where only the statistics of a subset of arms can be stored. A hierarchical learning policy that requires only a sublinear order of memory space in terms of the number of arms…

Machine Learning · Computer Science 2021-05-12 Xiao Xu , Qing Zhao

Reinforcement learning is well suited for optimizing policies of recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with the real environment, and thus are expensive in model…

Machine Learning · Computer Science 2020-01-22 Xueying Bai , Jian Guan , Hongning Wang

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult…

Machine Learning · Statistics 2018-12-18 Maria Dimakopoulou , Zhengyuan Zhou , Susan Athey , Guido Imbens

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

Motivated by the strategic participation of electricity producers in electricity day-ahead market, we study the problem of online learning in repeated multi-unit uniform price auctions focusing on the adversarial opposing bid setting. The…

Computer Science and Game Theory · Computer Science 2025-01-20 Marius Potfer , Dorian Baudry , Hugo Richard , Vianney Perchet , Cheng Wan

Off-policy evaluation (OPE) is the problem of estimating the value of a target policy from samples obtained via different policies. Recently, applying OPE methods for bandit problems has garnered attention. For the theoretical guarantees of…

Machine Learning · Computer Science 2020-10-26 Masahiro Kato , Kenshi Abe , Kaito Ariu , Shota Yasui

Computationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is not well-specified, the bandit algorithm may incur…

Machine Learning · Computer Science 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(2024) proposed the first best-of-both-worlds algorithm able…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

We introduce the factored bandits model, which is a framework for learning with limited (bandit) feedback, where actions can be decomposed into a Cartesian product of atomic actions. Factored bandits incorporate rank-1 bandits as a special…

Machine Learning · Computer Science 2018-10-30 Julian Zimmert , Yevgeny Seldin

We study the problem of minimizing polarization and disagreement in the Friedkin-Johnsen opinion dynamics model under incomplete information. Unlike prior work that assumes a static setting with full knowledge of agents' innate opinions, we…

Machine Learning · Computer Science 2026-03-09 Federico Cinus , Yuko Kuroki , Atsushi Miyauchi , Francesco Bonchi

We consider the problem of online learning where the sequence of actions played by the learner must adhere to an unknown safety constraint at every round. The goal is to minimize regret with respect to the best safe action in hindsight…

Machine Learning · Computer Science 2024-03-08 Karthik Sridharan , Seung Won Wilson Yoo

Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and…

Machine Learning · Computer Science 2015-03-17 Stephane Ross , Geoffrey J. Gordon , J. Andrew Bagnell

Stochastic linear bandits are a natural and well-studied model for structured exploration/exploitation problems and are widely used in applications such as online marketing and recommendation. One of the main challenges faced by…

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko