中文
相关论文

相关论文: Single Index Bandits: Generalized Linear Contextua…

200 篇论文

One of the primary challenges in large-scale distributed learning stems from stringent communication constraints. While several recent works address this challenge for static optimization problems, sequential decision-making under…

机器学习 · 计算机科学 2022-03-03 Aritra Mitra , Hamed Hassani , George J. Pappas

We consider combinatorial semi-bandits over a set of arms ${\cal X} \subset \{0,1\}^d$ where rewards are uncorrelated across items. For this problem, the algorithm ESCB yields the smallest known regret bound $R(T) = {\cal O}\Big( {d (\ln…

机器学习 · 统计学 2021-01-14 Thibaut Cuvelier , Richard Combes , Eric Gourdin

Information-directed sampling (IDS) is a powerful framework for solving bandit problems which has shown strong results in both Bayesian and frequentist settings. However, frequentist IDS, like many other bandit algorithms, requires that one…

机器学习 · 统计学 2025-03-10 Piotr M. Suder , Eric Laber

Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandits, which interpolates the regret for the worst-case regime…

机器学习 · 计算机科学 2023-02-22 Heyang Zhao , Jiafan He , Dongruo Zhou , Tong Zhang , Quanquan Gu

In this study, we explore a collaborative multi-agent stochastic linear bandit setting involving a network of $N$ agents that communicate locally to minimize their collective regret while keeping their expected cost under a specified…

机器学习 · 计算机科学 2024-10-24 Amirhossein Afsharrad , Parisa Oftadeh , Ahmadreza Moradipari , Sanjay Lall

We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex…

机器学习 · 计算机科学 2015-10-20 Huasen Wu , R. Srikant , Xin Liu , Chong Jiang

This paper investigates stochastic multi-armed bandit algorithms that are robust to adversarial attacks, where an attacker can first observe the learner's action and {then} alter their reward observation. We study two cases of this model,…

机器学习 · 计算机科学 2024-08-19 Xuchuang Wang , Jinhang Zuo , Xutong Liu , John C. S. Lui , Mohammad Hajiesmaili

We consider bandit optimization of a smooth reward function, where the goal is cumulative regret minimization. This problem has been studied for $\alpha$-H\"older continuous (including Lipschitz) functions with $0<\alpha\leq 1$. Our main…

机器学习 · 计算机科学 2020-12-14 Yusha Liu , Yining Wang , Aarti Singh

We consider a stochastic linear bandit problem in which the rewards are not only subject to random noise, but also adversarial attacks subject to a suitable budget $C$ (i.e., an upper bound on the sum of corruption magnitudes across the…

机器学习 · 统计学 2020-10-29 Ilija Bogunovic , Arpan Losalka , Andreas Krause , Jonathan Scarlett

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

机器学习 · 计算机科学 2026-05-08 Harin Lee , Min-hwan Oh

We study the problem of online generalized linear regression in the stochastic setting, where the label is generated from a generalized linear model with possibly unbounded additive noise. We provide a sharp analysis of the classical…

机器学习 · 计算机科学 2023-03-28 Heyang Zhao , Dongruo Zhou , Jiafan He , Quanquan Gu

We propose a new bootstrap-based online algorithm for stochastic linear bandit problems. The key idea is to adopt residual bootstrap exploration, in which the agent estimates the next step reward by re-sampling the residuals of mean reward…

机器学习 · 统计学 2022-06-20 Shuang Wu , Chi-Hua Wang , Yuantong Li , Guang Cheng

Recent growing adoption of experimentation in practice has led to a surge of attention to multiarmed bandits as a technique to reduce the opportunity cost of online experiments. In this setting, a decision-maker sequentially chooses among a…

机器学习 · 计算机科学 2022-04-04 Nima Hamidi , Mohsen Bayati

We consider the general (stochastic) contextual bandit problem under the realizability assumption, i.e., the expected reward, as a function of contexts and actions, belongs to a general function class $\mathcal{F}$. We design a fast and…

机器学习 · 计算机科学 2021-07-13 David Simchi-Levi , Yunzong Xu

Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. Despite the superior practical performance, their theoretical justification is less investigated in the literature, especially…

机器学习 · 统计学 2025-05-23 Ziyi Huang , Henry Lam , Haofeng Zhang

Stochastic linear bandits are a fundamental model for sequential decision making, where an agent selects a vector-valued action and receives a noisy reward with expected value given by an unknown linear function. Although well studied in…

机器学习 · 计算机科学 2025-06-23 Bruce Huang , Ruida Zhou , Lin F. Yang , Suhas Diggavi

We consider linear stochastic bandits where the set of actions is an ellipsoid. We provide the first known minimax optimal algorithm for this problem. We first derive a novel information-theoretic lower bound on the regret of any algorithm,…

机器学习 · 统计学 2025-02-25 Raymond Zhang , Hedi Hadiji , Richard Combes

We consider a collaborative online learning paradigm, wherein a group of agents connected through a social network are engaged in playing a stochastic multi-armed bandit game. Each time an agent takes an action, the corresponding reward is…

机器学习 · 计算机科学 2016-07-12 Ravi Kumar Kolla , Krishna Jagannathan , Aditya Gopalan

Contextual bandit with linear reward functions is among one of the most extensively studied models in bandit and online learning research. Recently, there has been increasing interest in designing \emph{locally private} linear contextual…

机器学习 · 统计学 2024-04-16 Jiachun Li , David Simchi-Levi , Yining Wang

We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies, whose expected cumulative reward over the course of $T$ rounds is maximum, and each has an expected cost below a…

机器学习 · 计算机科学 2020-06-20 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett , Heinrich Jiang