中文
相关论文

相关论文: Tracking Most Significant Shifts in Nonparametric …

200 篇论文

Logistic Bandits have recently attracted substantial attention, by providing an uncluttered yet challenging framework for understanding the impact of non-linearity in parametrized bandits. It was shown by Faury et al. (2020) that the…

机器学习 · 计算机科学 2021-03-10 Marc Abeille , Louis Faury , Clément Calauzènes

Lipschitz bandits is a prominent version of multi-armed bandits that studies large, structured action spaces such as the $[0,1]$ interval, where similar actions are guaranteed to have similar rewards. A central theme here is the adaptive…

机器学习 · 计算机科学 2025-06-13 Chara Podimata , Aleksandrs Slivkins

We study the benefits of sparsity in nonparametric contextual bandit problems, in which the set of candidate features is countably or uncountably infinite. Our contribution is two-fold. First, using a novel reduction to sequences of…

机器学习 · 统计学 2026-01-16 Hamish Flynn , Julia Olkhovskaya , Paul Rognon-Vael

We study the non-stationary stochastic multi-armed bandit problem, where the reward statistics of each arm may change several times during the course of learning. The performance of a learning algorithm is evaluated in terms of their…

机器学习 · 计算机科学 2022-03-09 Yasin Abbasi-Yadkori , Andras Gyorgy , Nevena Lazic

Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually…

机器学习 · 计算机科学 2018-05-25 Qingyun Wu , Naveen Iyer , Hongning Wang

Classic contextual bandit algorithms for linear models, such as LinUCB, assume that the reward distribution for an arm is modeled by a stationary linear regression. When the linear regression model is non-stationary over time, the regret of…

机器学习 · 统计学 2020-02-14 Qin Ding , Cho-Jui Hsieh , James Sharpnack

We propose the first contextual bandit algorithm that is parameter-free, efficient, and optimal in terms of dynamic regret. Specifically, our algorithm achieves dynamic regret $\mathcal{O}(\min\{\sqrt{ST},…

机器学习 · 计算机科学 2019-06-19 Yifang Chen , Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei

Consider a nonparametric contextual multi-arm bandit problem where each arm $a \in [K]$ is associated to a nonparametric reward function $f_a: [0,1] \to \mathbb{R}$ mapping from contexts to the expected reward. Suppose that there is a large…

机器学习 · 计算机科学 2019-08-06 Nirandika Wanigasekara , Christina Lee Yu

We analyze the $K$-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions. We attain tight results for top-arm identification and a sublinear regret of…

机器学习 · 计算机科学 2018-01-08 Melody Y. Guan , Heinrich Jiang

This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear…

机器学习 · 统计学 2018-07-17 Akshay Krishnamurthy , Zhiwei Steven Wu , Vasilis Syrgkanis

In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it…

机器学习 · 计算机科学 2022-07-19 Meena Jagadeesan , Tijana Zrnic , Celestine Mendler-Dünner

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are…

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…

机器学习 · 计算机科学 2022-07-14 Yinglun Zhu , Paul Mineiro

In this paper, we investigate the non-stationary combinatorial semi-bandit problem, both in the switching case and in the dynamic case. In the general case where (a) the reward function is non-linear, (b) arms may be probabilistically…

机器学习 · 计算机科学 2021-06-22 Wei Chen , Liwei Wang , Haoyu Zhao , Kai Zheng

Contextual bandit algorithms are extremely popular and widely used in recommendation systems to provide online personalised recommendations. A recurrent assumption is the stationarity of the reward function, which is rather unrealistic in…

机器学习 · 统计学 2020-04-29 Giuseppe Di Benedetto , Vito Bellini , Giovanni Zappella

We consider the classical stochastic multi-armed bandit problem with a constraint that limits the total cost incurred by switching between actions to be no larger than a given switching budget. For this problem, we prove matching upper and…

机器学习 · 计算机科学 2021-03-22 David Simchi-Levi , Yunzong Xu

A contextual bandit problem is studied in a highly non-stationary environment, which is ubiquitous in various recommender systems due to the time-varying interests of users. Two models with disjoint and hybrid payoffs are considered to…

机器学习 · 计算机科学 2020-03-03 Xiao Xu , Fang Dong , Yanghua Li , Shaojian He , Xin Li

Motivated by online recommendation and advertising systems, we consider a causal model for stochastic contextual bandits with a latent low-dimensional confounder. In our model, there are $L$ observed contexts and $K$ arms of the bandit. The…

机器学习 · 计算机科学 2016-10-28 Rajat Sen , Karthikeyan Shanmugam , Murat Kocaoglu , Alexandros G. Dimakis , Sanjay Shakkottai

We study the Lipschitz bandit problem, where a learner sequentially maximizes an unknown Lipschitz function $f$ over a domain $\mathcal{X} \subset [0,1]^d$ using noisy pointwise evaluations. Existing regret bounds are either worst-case,…

机器学习 · 统计学 2026-05-29 Marius Potfer , Vianney Perchet

We introduce a novel online learning framework that unifies and generalizes pre-established models, such as delayed and corrupted feedback, to encompass adversarial environments where action feedback evolves over time. In this setting, the…

机器学习 · 计算机科学 2024-05-28 Yogev Bar-On , Yishay Mansour