English
Related papers

Related papers: Sequential Probability Assignment with Contexts: M…

200 papers

We study contextual bandits in the stochastic i.i.d.\ setting, where a learner observes contexts drawn from an unknown distribution, selects actions from a finite set $A$, and aims to identify an approximately optimal policy from a given…

Machine Learning · Computer Science 2026-05-29 Liad Erez , Fan Chen , Alon Cohen , Tomer Koren , Yishay Mansour , Shay Moran , Alexander Rakhlin

We present a novel notion of complexity that interpolates between and generalizes some classic existing complexity notions in learning theory: for estimators like empirical risk minimization (ERM) with arbitrary bounded losses, it is upper…

Machine Learning · Computer Science 2017-10-24 Peter D. Grünwald , Nishant A. Mehta

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

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu

We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature…

Machine Learning · Computer Science 2026-05-18 Rahul Singh , Siddharth Chandak , Eric Moulines , Vivek S. Borkar , Nicholas Bambos

Sequential change-point detection when the distribution parameters are unknown is a fundamental problem in statistics and machine learning. When the post-change parameters are unknown, we consider a set of detection procedures based on…

Statistics Theory · Mathematics 2017-12-06 Yang Cao , Liyan Xie , Yao Xie , Huan Xu

In this paper, we study the contextual multinomial logit (MNL) bandit problem in which a learning agent sequentially selects an assortment based on contextual information, and user feedback follows an MNL choice model. There has been a…

Machine Learning · Statistics 2025-10-17 Joongkyu Lee , Min-hwan Oh

We introduce a novel online multitask setting. In this setting each task is partitioned into a sequence of segments that is unknown to the learner. Associated with each segment is a hypothesis from some hypothesis class. We give algorithms…

Machine Learning · Computer Science 2020-08-18 Mark Herbster , Stephen Pasteris , Lisa Tse

Recent work has proposed using Large Language Models (LLMs) to quantify narrative flow through a measure called sequentiality, which combines topic and contextual terms. A recent critique argued that the original results were confounded by…

Computation and Language · Computer Science 2025-11-13 Amal Sunny , Advay Gupta , Vishnu Sreekumar

Designing efficient general-purpose contextual bandit algorithms that work with large -- or even continuous -- action spaces would facilitate application to important scenarios such as information retrieval, recommendation systems, and…

Machine Learning · Computer Science 2022-07-14 Yinglun Zhu , Paul Mineiro

In many applications, e.g. in healthcare and e-commerce, the goal of a contextual bandit may be to learn an optimal treatment assignment policy at the end of the experiment. That is, to minimize simple regret. However, this objective…

Machine Learning · Computer Science 2023-11-06 Sanath Kumar Krishnamurthy , Ruohan Zhan , Susan Athey , Emma Brunskill

We address the problem of sequential prediction with expert advice in a non-stationary environment with long-term memory guarantees in the sense of Bousquet and Warmuth [4]. We give a linear-time algorithm that improves on the best known…

Machine Learning · Computer Science 2021-06-25 James Robinson , Mark Herbster

We study online learnability of a wide class of problems, extending the results of (Rakhlin, Sridharan, Tewari, 2010) to general notions of performance measure well beyond external regret. Our framework simultaneously captures such…

Machine Learning · Statistics 2011-03-25 Alexander Rakhlin , Karthik Sridharan , Ambuj Tewari

We consider the question of sequential prediction under the log-loss in terms of cumulative regret. Namely, given a hypothesis class of distributions, learner sequentially predicts the (distribution of the) next letter in sequence and its…

Machine Learning · Computer Science 2021-09-16 Meir Feder , Yury Polyanskiy

A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a…

Machine Learning · Computer Science 2025-04-30 Zihan Zhang , Yuxin Chen , Jason D. Lee , Simon S. Du

In this paper, we study gap-dependent regret guarantees for risk-sensitive reinforcement learning based on the entropic risk measure. We propose a novel definition of sub-optimality gaps, which we call cascaded gaps, and we discuss their…

Machine Learning · Computer Science 2022-03-08 Yingjie Fei , Ruitu Xu

We study reinforcement learning for episodic Markov Decision Processes (MDPs) whose transitions are modelled by a multinomial logistic (MNL) model. Existing algorithms for MNL mixture MDPs yield a regret of $\smash{\tilde{O}(dH^2\sqrt{T})}$…

Artificial Intelligence · Computer Science 2026-05-20 Pierre Boudart , Pierre Gaillard , Alessandro Rudi

Parameter estimation in Markov random fields (MRFs) is a difficult task, in which inference over the network is run in the inner loop of a gradient descent procedure. Replacing exact inference with approximate methods such as loopy belief…

Machine Learning · Computer Science 2012-06-18 Varun Ganapathi , David Vickrey , John Duchi , Daphne Koller

We study a nonparametric contextual bandit problem where the expected reward functions belong to a H\"older class with smoothness parameter $\beta$. We show how this interpolates between two extremes that were previously studied in…

Machine Learning · Statistics 2020-09-14 Yichun Hu , Nathan Kallus , Xiaojie Mao

We consider the reinforcement learning problem for the constrained Markov decision process (CMDP), which plays a central role in satisfying safety or resource constraints in sequential learning and decision-making. In this problem, we are…

Machine Learning · Computer Science 2025-11-19 Jiashuo Jiang , Yinyu Ye