English
Related papers

Related papers: Stronger Neyman Regret Guarantees for Adaptive Exp…

200 papers

In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The multi-batch reinforcement learning framework, where the agent…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Yuhang Jiang , Yuan Zhou , Xiangyang Ji

We address the problem of estimating heterogeneous treatment effects in panel data, adopting the popular Difference-in-Differences (DiD) framework under the conditional parallel trends assumption. We propose a novel doubly robust…

Machine Learning · Statistics 2025-04-29 Hui Lan , Haoge Chang , Eleanor Dillon , Vasilis Syrgkanis

Performative prediction is a recently proposed framework where predictions guide decision-making and hence influence future data distributions. Such performative phenomena are ubiquitous in various areas, such as transportation, finance,…

Machine Learning · Computer Science 2023-09-25 Wenjing Yan , Xuanyu Cao

The treatment assignment mechanism in a randomized clinical trial can be optimized for statistical efficiency within a specified class of randomization mechanisms. Optimal designs of this type have been characterized in terms of the…

Methodology · Statistics 2025-09-03 Wei Zhang , Zhiwei Zhang , Aiyi Liu

We consider the problem of the Zinkevich (2003)-style dynamic regret minimization in online learning with exp-concave losses. We show that whenever improper learning is allowed, a Strongly Adaptive online learner achieves the dynamic regret…

Machine Learning · Computer Science 2021-07-06 Dheeraj Baby , Yu-Xiang Wang

We study the problem of uncertainty quantification via prediction sets, in an online setting where the data distribution may vary arbitrarily over time. Recent work develops online conformal prediction techniques that leverage regret…

Machine Learning · Computer Science 2023-02-16 Aadyot Bhatnagar , Huan Wang , Caiming Xiong , Yu Bai

Robot reinforcement learning from demonstrations (RLfD) assumes that expert data is abundant; this is usually unrealistic in the real world given data scarcity as well as high collection cost. Furthermore, imitation learning algorithms…

Robotics · Computer Science 2026-04-07 Viet Dung Nguyen , Yuhang Song , Anh Nguyen , Jamison Heard , Reynold Bailey , Alexander Ororbia

We study the optimal batch-regret tradeoff for batch linear contextual bandits. For any batch number $M$, number of actions $K$, time horizon $T$, and dimension $d$, we provide an algorithm and prove its regret guarantee, which, due to…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Xiangyang Ji , Yuan Zhou

Adapting to a priori unknown noise level is a very important but challenging problem in sequential decision-making as efficient exploration typically requires knowledge of the noise level, which is often loosely specified. We report…

Machine Learning · Statistics 2024-06-11 Kwang-Sung Jun , Jungtaek Kim

In the bandits with knapsacks framework (BwK) the learner has $m$ resource-consumption (packing) constraints. We focus on the generalization of BwK in which the learner has a set of general long-term constraints. The goal of the learner is…

Machine Learning · Computer Science 2024-05-13 Martino Bernasconi , Matteo Castiglioni , Andrea Celli

We consider the adversarial multi-armed bandit problem under delayed feedback. We analyze variants of the Exp3 algorithm that tune their step-size using only information (about the losses and delays) available at the time of the decisions,…

Machine Learning · Computer Science 2020-10-14 András György , Pooria Joulani

Ranking algorithms are fundamental to various online platforms across e-commerce sites to content streaming services. Our research addresses the challenge of adaptively ranking items from a candidate pool for heterogeneous users, a key…

Machine Learning · Computer Science 2024-06-10 Jingyuan Wang , Perry Dong , Ying Jin , Ruohan Zhan , Zhengyuan Zhou

This article proposes doubly robust estimators for the average treatment effect on the treated (ATT) in difference-in-differences (DID) research designs. In contrast to alternative DID estimators, the proposed estimators are consistent if…

Econometrics · Economics 2020-05-07 Pedro H. C. Sant'Anna , Jun B. Zhao

Existing algorithms for online conformal prediction -- guaranteeing marginal coverage in adversarial settings -- are variants of online gradient descent (OGD), but their analyses of worst-case coverage do not follow from the regret…

Machine Learning · Computer Science 2025-02-18 Ramya Ramalingam , Shayan Kiyani , Aaron Roth

We study the $K$-armed logistic bandit problem, where at each round, the agent observes $K$ feature vectors associated with $K$ actions. Existing approaches that achieve a rate-optimal $\tilde{\mathcal{O}}(\sqrt{dT})$ regret bound rely…

Machine Learning · Computer Science 2026-05-01 Seoungbin Bae , Dabeen Lee

Developing targeted therapies based on patients' baseline characteristics and genomic profiles such as biomarkers has gained growing interests in recent years. Depending on patients' clinical characteristics, the expression of specific…

Applications · Statistics 2019-02-26 Yanxun Xu , Florica Constantine , Yuan Yuan , Yili L. Pritchett

We study the stochastic multi-armed bandit problem and design new policies that enjoy both worst-case optimality for expected regret and light-tailed risk for regret distribution. Specifically, our policy design (i) enjoys the worst-case…

Machine Learning · Statistics 2024-07-23 David Simchi-Levi , Zeyu Zheng , Feng Zhu

We design differentially private algorithms for the problem of prediction with expert advice under dynamic regret, also known as tracking the best expert. Our work addresses three natural types of adversaries, stochastic with shifting…

Machine Learning · Computer Science 2025-03-14 Aadirupa Saha , Vinod Raman , Hilal Asi

Inspired by online learning, data-dependent regret has recently been proposed as a criterion for controller design. In the regret-optimal control paradigm, causal controllers are designed to minimize regret against a hypothetical optimal…

Optimization and Control · Mathematics 2022-09-15 Gautam Goel , Babak Hassibi

Policy design in non-stationary Markov Decision Processes (MDPs) is inherently challenging due to the complexities introduced by time-varying system transition and reward, which make it difficult for learners to determine the optimal…

Machine Learning · Computer Science 2025-11-17 Ziyi Zhang , Yorie Nakahira , Guannan Qu