中文
相关论文

相关论文: Thompson Sampling Regret Bounds for Contextual Ban…

200 篇论文

We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with binary losses and adversarially-selected contexts. We adapt the information-theoretic perspective of \cite{RvR16} to the contextual setting…

机器学习 · 计算机科学 2023-03-07 Gergely Neu , Julia Olkhovskaya , Matteo Papini , Ludovic Schwartz

Thompson Sampling, one of the oldest heuristics for solving multi-armed bandits, has recently been shown to demonstrate state-of-the-art performance. The empirical success has led to great interests in theoretical understanding of this…

机器学习 · 计算机科学 2013-10-29 Lihong Li

Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better…

机器学习 · 计算机科学 2014-02-04 Shipra Agrawal , Navin Goyal

Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both…

机器学习 · 计算机科学 2022-01-03 Weitong Zhang , Dongruo Zhou , Lihong Li , Quanquan Gu

Thompson Sampling has been widely used for contextual bandit problems due to the flexibility of its modeling power. However, a general theory for this class of methods in the frequentist setting is still lacking. In this paper, we present a…

机器学习 · 计算机科学 2021-10-05 Tong Zhang

This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems. It builds upon the information-theoretic framework of [Russo and Van Roy, 2015] and, more specifically, on the rate-distortion…

This paper studies the Bayesian regret of the Thompson Sampling algorithm for bandit problems, building on the information-theoretic framework introduced by Russo and Van Roy (2015). Specifically, it extends the rate-distortion analysis of…

机器学习 · 统计学 2025-02-05 Amaury Gouverneur , Borja Rodriguez Gálvez , Tobias Oechtering , Mikael Skoglund

We explore a stochastic contextual linear bandit problem where the agent observes a noisy, corrupted version of the true context through a noise channel with an unknown noise parameter. Our objective is to design an action policy that can…

机器学习 · 计算机科学 2024-03-26 Sharu Theresa Jose , Shana Moothedath

We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logistic function, $\exp(\beta \langle a, \theta…

Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better…

机器学习 · 计算机科学 2012-09-18 Shipra Agrawal , Navin Goyal

Contextual bandits constitute a classical framework for decision-making under uncertainty. In this setting, the goal is to learn the arms of highest reward subject to contextual information, while the unknown reward parameters of each arm…

机器学习 · 统计学 2024-02-19 Hongju Park , Mohamad Kazem Shirani Faradonbeh

We consider the stochastic linear contextual bandit problem with high-dimensional features. We analyze the Thompson sampling algorithm using special classes of sparsity-inducing priors (e.g., spike-and-slab) to model the unknown parameter…

机器学习 · 统计学 2023-01-31 Sunrit Chakraborty , Saptarshi Roy , Ambuj Tewari

We study Thompson Sampling-based algorithms for stochastic bandits with bounded rewards. As the existing problem-dependent regret bound for Thompson Sampling with Gaussian priors [Agrawal and Goyal, 2017] is vacuous when $T \le 288 e^{64}$,…

机器学习 · 计算机科学 2024-05-03 Bingshan Hu , Zhiming Huang , Tianyue H. Zhang , Mathias Lécuyer , Nidhi Hegde

A challenging aspect of the bandit problem is that a stochastic reward is observed only for the chosen arm and the rewards of other arms remain missing. The dependence of the arm choice on the past context and reward pairs compounds the…

机器学习 · 统计学 2023-05-02 Wonyoung Kim , Gi-soo Kim , Myunghee Cho Paik

We consider the stochastic multi-armed bandit problem with a prior distribution on the reward distributions. We are interested in studying prior-free and prior-dependent regret bounds, very much in the same spirit as the usual…

机器学习 · 统计学 2013-10-04 Sébastien Bubeck , Che-Yu Liu

Stochastic rising rested bandit (SRRB) is a setting where the arms' expected rewards increase as they are pulled. It models scenarios in which the performances of the different options grow as an effect of an underlying learning process…

机器学习 · 统计学 2025-05-21 Marco Fiandri , Alberto Maria Metelli , Francesco Trovò

We address online combinatorial optimization when the player has a prior over the adversary's sequence of losses. In this framework, Russo and Van Roy proposed an information-theoretic analysis of Thompson Sampling based on the information…

机器学习 · 计算机科学 2022-04-05 Sébastien Bubeck , Mark Sellke

In linear contextual bandits, the objective is to select actions that maximize cumulative rewards, modeled as a linear function with unknown parameters. Although Thompson Sampling performs well empirically, it does not achieve optimal…

机器学习 · 统计学 2025-06-18 Wonyoung Kim

Motivated by the pressing need for efficient optimization in online recommender systems, we revisit the cascading bandit model proposed by Kveton et al. (2015). While Thompson sampling (TS) algorithms have been shown to be empirically…

机器学习 · 计算机科学 2021-05-18 Zixin Zhong , Wang Chi Cheung , Vincent Y. F. Tan

Non-stationarity is ubiquitous in human behavior and addressing it in the contextual bandits is challenging. Several works have addressed the problem by investigating semi-parametric contextual bandits and warned that ignoring…

机器学习 · 统计学 2022-05-18 Young-Geun Choi , Gi-Soo Kim , Seunghoon Paik , Myunghee Cho Paik
‹ 上一页 1 2 3 10 下一页 ›