中文
相关论文

相关论文: Efficient Online Conformal Selection with Limited …

200 篇论文

We present online boosting algorithms for multiclass classification with bandit feedback, where the learner only receives feedback about the correctness of its prediction. We propose an unbiased estimate of the loss using a randomized…

机器学习 · 统计学 2019-02-26 Daniel T. Zhang , Young Hun Jung , Ambuj Tewari

We propose information-directed sampling -- a new approach to online optimization problems in which a decision-maker must balance between exploration and exploitation while learning from partial feedback. Each action is sampled in a manner…

机器学习 · 计算机科学 2017-07-10 Daniel Russo , Benjamin Van Roy

We study the problem of conformal prediction in a novel online framework that directly optimizes efficiency. In our problem, we are given a target miscoverage rate $\alpha > 0$, and a time horizon $T$. On each day $t \le T$ an algorithm…

机器学习 · 计算机科学 2025-10-23 Vaidehi Srinivas

We study the contextual multi-armed bandit problem with a finite context space (a.k.a. subpopulations), where the learner recommends a best action for each context and is evaluated by context-weighted simple regret. Our guarantees are…

机器学习 · 计算机科学 2026-05-20 Mohammad Shahverdikondori , Jalal Etesami , Negar Kiyavash

Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…

人工智能 · 计算机科学 2024-06-10 Federico Malato , Ville Hautamaki

We consider the problem of adversarial bandit convex optimization, that is, online learning over a sequence of arbitrary convex loss functions with only one function evaluation for each of them. While all previous works assume known and…

机器学习 · 计算机科学 2022-02-15 Haipeng Luo , Mengxiao Zhang , Peng Zhao

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…

机器学习 · 计算机科学 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

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…

机器学习 · 计算机科学 2022-05-11 Claudia Roberts , Maria Dimakopoulou , Qifeng Qiao , Ashok Chandrashekhar , Tony Jebara

In recent years, preference-based human feedback mechanisms have become essential for enhancing model performance across diverse applications, including conversational AI systems such as ChatGPT. However, existing approaches often neglect…

人工智能 · 计算机科学 2025-02-14 Raihan Seraj , Lili Meng , Tristan Sylvain

Adapting machine translation systems in the real world is a difficult problem. In contrast to offline training, users cannot provide the type of fine-grained feedback (such as correct translations) typically used for improving the system.…

计算与语言 · 计算机科学 2020-09-03 Jason Naradowsky , Xuan Zhang , Kevin Duh

We study risk-aware offline policy learning, aiming to learn a decision rule from logged data that is optimal under general risk criteria. This problem is crucial in high-stakes domains where online interaction is infeasible and adverse…

机器学习 · 统计学 2026-05-18 Yilong Wan , Yuqiang Li , Xianyi Wu

Contextual bandits serve as a fundamental algorithmic framework for optimizing recommendation decisions online. Though extensive attention has been paid to tailoring contextual bandits for recommendation applications, the "herding effects"…

机器学习 · 计算机科学 2024-08-29 Luyue Xu , Liming Wang , Hong Xie , Mingqiang Zhou

AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding…

人工智能 · 计算机科学 2018-09-18 Avinash Balakrishnan , Djallel Bouneffouf , Nicholas Mattei , Francesca Rossi

Motivated by online recommendation systems, we propose the problem of finding the optimal policy in multitask contextual bandits when a small fraction $\alpha < 1/2$ of tasks (users) are arbitrary and adversarial. The remaining fraction of…

机器学习 · 计算机科学 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

We propose a general framework for studying adaptive regret bounds in the online learning framework, including model selection bounds and data-dependent bounds. Given a data- or model-dependent bound we ask, "Does there exist some algorithm…

机器学习 · 计算机科学 2020-02-14 Dylan J. Foster , Alexander Rakhlin , Karthik Sridharan

We consider the problem of adversarial (non-stochastic) online learning with partial information feedback, where at each round, a decision maker selects an action from a finite set of alternatives. We develop a black-box approach for such…

机器学习 · 计算机科学 2021-07-28 Thodoris Lykouris , Karthik Sridharan , Eva Tardos

We consider the problem of online boosting for regression tasks, when only limited information is available to the learner. We give an efficient regret minimization method that has two implications: an online boosting algorithm with noisy…

机器学习 · 计算机科学 2020-07-24 Nataly Brukhim , Elad Hazan

Information-directed sampling (IDS) has recently demonstrated its potential as a data-efficient reinforcement learning algorithm. However, it is still unclear what is the right form of information ratio to optimize when contextual…

机器学习 · 计算机科学 2022-06-10 Botao Hao , Tor Lattimore , Chao Qin

We design and implement an adaptive experiment (a ``contextual bandit'') to learn a targeted treatment assignment policy, where the goal is to use a participant's survey responses to determine which charity to expose them to in a donation…

Most off-policy evaluation methods for contextual bandits have focused on the expected outcome of a policy, which is estimated via methods that at best provide only asymptotic guarantees. However, in many applications, the expectation may…

机器学习 · 统计学 2022-10-27 Muhammad Faaiz Taufiq , Jean-Francois Ton , Rob Cornish , Yee Whye Teh , Arnaud Doucet