Search Results for author: Weina Wang

Found 6 papers, 0 papers with code

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption

no code implementations31 May 2023 Yige Hong, Qiaomin Xie, Yudong Chen, Weina Wang

In both settings, we establish the first asymptotic optimality result that does not require UGAP.

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

no code implementations25 May 2023 Honghao Wei, Xin Liu, Weina Wang, Lei Ying

This method significantly improves learning by reducing the sample complexity such that the dataset only needs to have sufficient coverage of the stochastic states.


Job Dispatching Policies for Queueing Systems with Unknown Service Rates

no code implementations8 Jun 2021 Tuhinangshu Choudhury, Gauri Joshi, Weina Wang, Sanjay Shakkottai

In multi-server queueing systems where there is no central queue holding all incoming jobs, job dispatching policies are used to assign incoming jobs to the queue at one of the servers.

On the Privacy-Utility Tradeoff in Peer-Review Data Analysis

no code implementations29 Jun 2020 Wenxin Ding, Nihar B. Shah, Weina Wang

The crux of the framework lies in recognizing that a part of the data pertaining to the reviews is already available in public, and we use this information to post-process the data released by any privacy mechanism in a manner that improves the accuracy (utility) of the data while retaining the privacy guarantees.

Privacy Preserving

QuickStop: A Markov Optimal Stopping Approach for Quickest Misinformation Detection

no code implementations4 Mar 2019 Honghao Wei, Xiaohan Kang, Weina Wang, Lei Ying

The algorithm consists of an offline machine learning algorithm for learning the probabilistic information spreading model and an online optimal stopping algorithm to detect misinformation.


Almost Boltzmann Exploration

no code implementations25 Jan 2019 Harsh Gupta, Seo Taek Kong, R. Srikant, Weina Wang

In this paper, we show that a simple modification to Boltzmann exploration, motivated by a variation of the standard doubling trick, achieves $O(K\log^{1+\alpha} T)$ regret for a stochastic MAB problem with $K$ arms, where $\alpha>0$ is a parameter of the algorithm.

Multi-Armed Bandits

Cannot find the paper you are looking for? You can Submit a new open access paper.