44 citations · 93 across the 21 of their papers we have counts for
21 papers
Stochastic Graph Bandit Learning with Side-Observations
Xueping Gong, Jiheng Zhang
In this paper, we investigate the stochastic contextual bandit with general function space and graph feedback. We propose an algorithm that addresses this problem by adapting to bo…
Efficient Transfer Learning via Causal Bounds
Xueping Gong, Wei You, Jiheng Zhang
Transfer learning seeks to accelerate sequential decision-making by leveraging offline data from related agents. However, data from heterogeneous sources that differ in observed fe…
Debiasing Recommendation by Learning Identifiable Latent Confounders
Qing Zhang, Xiaoying Zhang, Yang Liu +4
Recommendation systems aim to predict users' feedback on items not exposed to them. Confounding bias arises due to the presence of unmeasured variables (e.g., the socio-economic st…
Single-Trajectory Distributionally Robust Reinforcement Learning
Zhipeng Liang, Xiaoteng Ma, Jose Blanchet +2
To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) ha…
Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles
Yuxuan Han, Jialin Zeng, Yang Wang +2
We study the stochastic contextual bandit with knapsacks (CBwK) problem, where each action, taken upon a context, not only leads to a random reward but also costs a random resource…
Dual Instrumental Method for Confounded Kernelized Bandits
Xueping Gong, Jiheng Zhang
The contextual bandit problem is a theoretically justified framework with wide applications in various fields. While the previous study on this problem usually requires independenc…
Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation
Xiaoteng Ma, Zhipeng Liang, Jose Blanchet +5
Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment…
On Private Online Convex Optimization: Optimal Algorithms in -Geometry and High Dimensional Contextual Bandits
Yuxuan Han, Zhicong Liang, Zhipeng Liang +3
Differentially private (DP) stochastic convex optimization (SCO) is ubiquitous in trustworthy machine learning algorithm design. This paper studies the DP-SCO problem with streamin…
Improving Blockchain Consistency Bound by Assigning Weights to Random Blocks
Qing Zhang, Xueping Gong, Huizhong Li +2
Blockchains based on the celebrated Nakamoto consensus protocol have shown promise in several applications, including cryptocurrencies. However, these blockchains have inherent sca…
Generalized Linear Bandits with Local Differential Privacy
Yuxuan Han, Zhipeng Liang, Yang Wang +1
Contextual bandit algorithms are useful in personalized online decision-making. However, many applications such as personalized medicine and online advertising require the utilizat…
Consensus Mechanism Design based on Structured Directed Acyclic Graphs
Jiahao He, Guangju Wang, Guangyuan Zhang +1
We introduce a structure for the directed acyclic graph (DAG) and a mechanism design based on that structure so that peers can reach consensus at large scale based on proof of work…
A Note on Many-server Fluid Models with Time-varying Arrivals
Zhenghua Long, Jiheng Zhang
We extend the measure-valued fluid model, which tracks residuals of patience and service times, to allow for time-varying arrivals. The fluid model can be characterized by a one-di…
Heavy-traffic approximations for a layered network with limited resources
Angelos Aveklouris, Maria Vlasiou, Jiheng Zhang +1
Motivated by a web-server model, we present a queueing network consisting of two layers. The first layer incorporates the arrival of customers at a network of two single-server nod…
Instantaneous Control of Brownian Motion with a Positive Lead Time
Zhen Xu, Jiheng Zhang, Rachel Q. Zhang
Consider a storage system where the content is driven by a Brownian motion absent control. At any time, one may increase or decrease the content at a cost proportional to the amoun…
Insensitivity of Proportional Fairness in Critically Loaded Bandwidth Sharing Networks
Maria Vlasiou, Jiheng Zhang, Bert Zwart
Proportional fairness is a popular service allocation mechanism to describe and analyze the performance of data networks at flow level. Recently, several authors have shown that th…
Approximations and Optimal Control for State-dependent Limited Processor Sharing Queues
Varun Gupta, Jiheng Zhang
The paper studies approximations and control of a processor sharing (PS) server where the service rate depends on the number of jobs occupying the server. The control of such a sys…
Separation of timescales in a two-layered network
Maria Vlasiou, Jiheng Zhang, Bert Zwart
We investigate a computer network consisting of two layers occurring in, for example, application servers. The first layer incorporates the arrival of jobs at a network of multi-se…
Convergence to Equilibrium States for Fluid Models of Many-server Queues with Abandonment
Zhenghua Long, Jiheng Zhang
Fluid models have become an important tool for the study of many-server queues with general service and patience time distributions. The equilibrium state of a fluid model has been…
A Unified Approach to Diffusion Analysis of Queues with General Patience-time Distributions
Junfei Huang, Hanqin Zhang, Jiheng Zhang
We propose a unified approach to establishing diffusion approximations for queues with impatient customers within a general framework of scaling customer patience time. The approac…
Diffusion limits of limited processor sharing queues
Jiheng Zhang, J. G. Dai, Bert Zwart
We consider a processor sharing queue where the number of jobs served at any time is limited to , with the excess jobs waiting in a buffer. We use random counting measures on th…
Fluid Models of Many-server Queues with Abandonment
Jiheng Zhang
We study many-server queues with abandonment in which customers have general service and patience time distributions. The dynamics of the system are modeled using measure- valued p…