中文
相关论文

相关论文: Thompson Sampling Achieves $\tilde O(\sqrt{T})$ Re…

200 篇论文

Adaptively controlling and minimizing regret in unknown dynamical systems while controlling the growth of the system state is crucial in real-world applications. In this work, we study the problem of stabilization and regret minimization of…

系统与控制 · 电气工程与系统科学 2022-02-10 Jafar Abbaszadeh Chekan , Kamyar Azizzadenesheli , Cedric Langbort

We study the problem of adaptive control of a high dimensional linear quadratic (LQ) system. Previous work established the asymptotic convergence to an optimal controller for various adaptive control schemes. More recently, for the average…

机器学习 · 统计学 2013-03-26 Morteza Ibrahimi , Adel Javanmard , Benjamin Van Roy

This work tackles the complexities of multi-player scenarios in \emph{unknown games}, where the primary challenge lies in navigating the uncertainty of the environment through bandit feedback alongside strategic decision-making. We…

机器学习 · 计算机科学 2024-02-27 Yingru Li , Liangqi Liu , Wenqiang Pu , Hao Liang , Zhi-Quan Luo

We study the logistic bandit, in which rewards are binary with success probability $\exp(\beta a^\top \theta) / (1 + \exp(\beta a^\top \theta))$ and actions $a$ and coefficients $\theta$ are within the $d$-dimensional unit ball. While prior…

机器学习 · 统计学 2019-05-14 Shi Dong , Tengyu Ma , Benjamin Van Roy

We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the loss functions are strongly convex or exp-concave, we…

机器学习 · 计算机科学 2021-11-24 Dheeraj Baby , Hilaf Hasson , Yuyang Wang

The problem of two-sided matching markets has a wide range of real-world applications and has been extensively studied in the literature. A line of recent works have focused on the problem setting where the preferences of one-side market…

机器学习 · 计算机科学 2022-05-03 Fang Kong , Junming Yin , Shuai Li

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

The literature on bandit learning and regret analysis has focused on contexts where the goal is to converge on an optimal action in a manner that limits exploration costs. One shortcoming imposed by this orientation is that it does not…

机器学习 · 计算机科学 2017-05-01 Daniel Russo , David Tse , Benjamin Van Roy

We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP. Compared with the GP upper confidence bound (GP-UCB) with…

机器学习 · 统计学 2026-03-11 Shion Takeno , Shogo Iwazaki

We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a…

机器学习 · 统计学 2017-05-26 Kirthevasan Kandasamy , Akshay Krishnamurthy , Jeff Schneider , Barnabas Poczos

This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm,…

机器学习 · 计算机科学 2021-11-10 Priyank Agrawal , Jinglin Chen , Nan Jiang

Thompson Sampling is one of the most widely used and studied bandit algorithms, known for its simple structure, low regret performance, and solid theoretical guarantees. Yet, in stark contrast to most other families of bandit algorithms,…

机器学习 · 计算机科学 2026-05-28 Yanlin Qu , Hongseok Namkoong , Assaf Zeevi

In stochastic bandit problems, a Bayesian policy called Thompson sampling (TS) has recently attracted much attention for its excellent empirical performance. However, the theoretical analysis of this policy is difficult and its asymptotic…

统计理论 · 数学 2013-11-11 Junya Honda , Akimichi Takemura

Learning how to effectively control unknown dynamical systems is crucial for intelligent autonomous systems. This task becomes a significant challenge when the underlying dynamics are changing with time. Motivated by this challenge, this…

机器学习 · 计算机科学 2025-10-21 Yahya Sattar , Zhe Du , Davoud Ataee Tarzanagh , Laura Balzano , Necmiye Ozay , Samet Oymak

Linear Quadratic Regulator (LQR) and Linear Quadratic Gaussian (LQG) control are foundational and extensively researched problems in optimal control. We investigate LQR and LQG problems with semi-adversarial perturbations and time-varying…

机器学习 · 计算机科学 2023-10-26 Y. Jennifer Sun , Stephen Newman , Elad Hazan

Most existing approximate Thompson Sampling (TS) algorithms for multi-armed bandits use Stochastic Gradient Langevin Dynamics (SGLD) or its variants in each round to sample from the posterior, relaxing the need for conjugacy assumptions…

机器学习 · 计算机科学 2025-10-07 Weixin Wang , Haoyang Zheng , Guang Lin , Wei Deng , Pan Xu

This paper addresses the problem of learning to sparsify stochastic linear bandits, where a decision-maker sequentially selects actions from a high-dimensional space subject to a sparsity constraint on the number of nonzero elements in the…

机器学习 · 计算机科学 2026-05-12 Zhengmiao Wang , Ming Chi , Zhi-Wei Liu , Lintao Ye , Carla Fabiana Chiasserini

We consider a non-stationary two-armed bandit framework and propose a change-detection based Thompson sampling (TS) algorithm, named TS with change-detection (TS-CD), to keep track of the dynamic environment. The non-stationarity is modeled…

机器学习 · 计算机科学 2020-09-09 Gourab Ghatak

We give a randomized online algorithm that guarantees near-optimal $\widetilde O(\sqrt T)$ expected swap regret against any sequence of $T$ adaptively chosen Lipschitz convex losses on the unit interval. This improves the previous best…

机器学习 · 计算机科学 2026-02-10 Lunjia Hu , Jon Schneider , Yifan Wu

In model-based solution approaches to the problem of learning in an unknown environment, exploring to learn the model parameters takes a toll on the regret. The optimal performance with respect to regret or PAC bounds is achievable, if the…

机器学习 · 计算机科学 2015-10-13 P. Prasanna , Sarath Chandar , Balaraman Ravindran