Výsledky vyhledávání - "Zhang Raymond"

Report

Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox

We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the "mismatched s

Externí odkaz: http://arxiv.org/abs/2410.05441

Zobrazit plný text záznamu

Report

ACPO: AI-Enabled Compiler-Driven Program Optimization

Autor: Ashouri, Amir H., Manzoor, Muhammad Asif, Vu, Duc Minh, Zhang, Raymond, Wang, Ziwen, Zhang, Angel, Chan, Bryan, Czajkowski, Tomasz S., Gao, Yaoqing

The key to performance optimization of a program is to decide correctly when a certain transformation should be applied by a compiler. This is an ideal opportunity to apply machine-learning models to speed up the tuning process; while this realizatio

Externí odkaz: http://arxiv.org/abs/2312.09982

Zobrazit plný text záznamu

Report

A Simple Time-Dependent Method for Calculating Spirals: Applications to Eccentric Planets in Protoplanetary discs

Autor: Zhu, Zhaohuan, Zhang, Raymond M.

Spirals in protoplanetary discs have been used to locate the potential planet in discs. Since only the spiral shape from a circularly orbiting perturber is known, most previous works assume that the planet is in a circular orbit. We develop a simple

Externí odkaz: http://arxiv.org/abs/2112.03311

Zobrazit plný text záznamu

Report

Reinforcement Learning for Traffic Signal Control: Comparison with Commercial Systems

Autor: Cabrejas-Egea, Alvaro, Zhang, Raymond, Walton, Neil

Recently, Intelligent Transportation Systems are leveraging the power of increased sensory coverage and computing power to deliver data-intensive solutions achieving higher levels of performance than traditional systems. Within Traffic Signal Control

Externí odkaz: http://arxiv.org/abs/2104.10455

Zobrazit plný text záznamu

Report

On the Suboptimality of Thompson Sampling in High Dimensions

Autor: Zhang, Raymond, Combes, Richard

In this paper we consider Thompson Sampling (TS) for combinatorial semi-bandits. We demonstrate that, perhaps surprisingly, TS is sub-optimal for this problem in the sense that its regret scales exponentially in the ambient dimension, and its minimax

Externí odkaz: http://arxiv.org/abs/2102.05502

Zobrazit plný text záznamu