English
Related papers

Related papers: Top-Two Thompson Sampling for Contextual Top-mc Se…

200 papers

We propose a sampling-based trajectory optimization methodology for constrained problems. We extend recent works on stochastic search to deal with box control constraints,as well as nonlinear state constraints for discrete dynamical…

Optimization and Control · Mathematics 2019-11-13 George I. Boutselis , Ziyi Wang , Evangelos A. Theodorou

Variance reduction techniques have been successfully applied to temporal-difference (TD) learning and help to improve the sample complexity in policy evaluation. However, the existing work applied variance reduction to either the less…

Machine Learning · Computer Science 2023-05-23 Shaocong Ma , Yi Zhou , Shaofeng Zou

Sequential optimization methods are often confronted with the curse of dimensionality in high-dimensional spaces. Current approaches under the Gaussian process framework are still burdened by the computational complexity of tracking…

Machine Learning · Computer Science 2024-01-08 Zeji Yi , Yunyue Wei , Chu Xin Cheng , Kaibo He , Yanan Sui

In this paper, we introduce and analyze a variant of the Thompson sampling (TS) algorithm for contextual bandits. At each round, traditional TS requires samples from the current posterior distribution, which is usually intractable. To…

Machine Learning · Statistics 2024-07-23 Pierre Clavier , Tom Huix , Alain Durmus

We consider incentivized exploration: a version of multi-armed bandits where the choice of arms is controlled by self-interested agents, and the algorithm can only issue recommendations. The algorithm controls the flow of information, and…

Computer Science and Game Theory · Computer Science 2022-06-14 Mark Sellke , Aleksandrs Slivkins

This paper considers data-driven chance-constrained stochastic optimization problems in a Bayesian framework. Bayesian posteriors afford a principled mechanism to incorporate data and prior knowledge into stochastic optimization problems.…

Statistics Theory · Mathematics 2023-08-07 Prateek Jaiswal , Harsha Honnappa , Vinayak A. Rao

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to…

Computation and Language · Computer Science 2024-04-03 Bingsheng Yao , Guiming Chen , Ruishi Zou , Yuxuan Lu , Jiachen Li , Shao Zhang , Yisi Sang , Sijia Liu , James Hendler , Dakuo Wang

Joint optimization of scheduling and estimation policies is considered for a system with two sensors and two non-collocated estimators. Each sensor produces an independent and identically distributed sequence of random variables, and each…

Systems and Control · Electrical Eng. & Systems 2019-08-19 Marcos M. Vasconcelos , Mukul Gagrani , Ashutosh Nayyar , Urbashi Mitra

We consider the popular tree-based search strategy within the framework of reinforcement learning, the Monte Carlo Tree Search (MCTS), in the context of finite-horizon Markov decision process. We propose a dynamic sampling tree policy that…

Artificial Intelligence · Computer Science 2023-05-09 Gongbo Zhang , Yijie Peng , Yilong Xu

We study sequential decision making in environments where rewards are only partially observed, but can be modeled as a function of observed contexts and the chosen action by the decision maker. This setting, known as contextual bandits,…

Methodology · Statistics 2015-03-11 Miroslav Dudík , Dumitru Erhan , John Langford , Lihong Li

Faced with massive data, subsampling is a commonly used technique to improve computational efficiency, and using nonuniform subsampling probabilities is an effective approach to improve estimation efficiency. For computational efficiency,…

Statistics Theory · Mathematics 2022-05-19 Jing Wang , Jiahui Zou , HaiYing Wang

In this paper, we propose a new recommendation algorithm for addressing the problem of two-sided online matching markets with complementary preferences and quota constraints, where agents' preferences are unknown a priori and must be…

Machine Learning · Statistics 2024-05-30 Yuantong Li , Guang Cheng , Xiaowu Dai

Statistical model checking avoids the exponential growth of states associated with probabilistic model checking by estimating properties from multiple executions of a system and by giving results within confidence bounds. Rare properties…

Performance · Computer Science 2012-01-26 Cyrille Jégourel , Axel Legay , Sean Sedwards

Bayesian optimization methods allocate limited sampling budgets to maximize expensive-to-evaluate functions. One-step-lookahead policies are often used, but computing optimal multi-step-lookahead policies remains a challenge. We consider a…

Optimization and Control · Mathematics 2016-07-13 J. Massey Cashore , Lemuel Kumarga , Peter I. Frazier

Optimal stopping is the problem of deciding when to stop a stochastic system to obtain the greatest reward, arising in numerous application areas such as finance, healthcare and marketing. State-of-the-art methods for high-dimensional…

Optimization and Control · Mathematics 2020-01-01 Dragos Florin Ciocan , Velibor V. Mišić

Thompson sampling (TS) has optimal regret and excellent empirical performance in multi-armed bandit problems. Yet, in Bayesian optimization, TS underperforms popular acquisition functions (e.g., EI, UCB). TS samples arms according to the…

Machine Learning · Statistics 2024-12-02 David Sweet

Additive feature explanations rely primarily on game-theoretic notions such as the Shapley value by viewing features as cooperating players. The Shapley value's popularity in and outside of explainable AI stems from its axiomatic…

Machine Learning · Computer Science 2025-07-23 Patrick Kolpaczki , Tim Nielen , Eyke Hüllermeier

We study sequential experiments where sampling is costly and a decision-maker aims to determine the best treatment for full scale implementation by (1) adaptively allocating units between two possible treatments, and (2) stopping the…

Econometrics · Economics 2025-05-06 Karun Adusumilli

Optimization of expensive computer models with the help of Gaussian process emulators in now commonplace. However, when several (competing) objectives are considered, choosing an appropriate sampling strategy remains an open question. We…

Optimization and Control · Mathematics 2013-10-03 Victor Picheny

Originally motivated by default risk management applications, this paper investigates a novel problem, referred to as the profitable bandit problem here. At each step, an agent chooses a subset of the K possible actions. For each action…

Machine Learning · Statistics 2018-05-09 Mastane Achab , Stephan Clémençon , Aurélien Garivier
‹ Prev 1 8 9 10 Next ›