Jiawei Zhou

Jiawei Zhou

Auto-generated profile, based on publicly available information

Jiawei Zhou

Applied Math and Statistics, Stony Brook University, Stony Brook, New York, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 August 2025
Verified
Conference Paper
Open access
ZWZhaodong Wang
Zhaodong Wang
SLSamuel Lin
Samuel Lin
GYGuanqing Yan
Guanqing Yan
SGSoudeh Ghorbani
Soudeh Ghorbani
MYMinlan Yu
Minlan Yu
YZYing Zhang
Ying Zhang

11 January 2023 in IEEE Transactions on Games
Verified
Journal Article
Closed access
YXYufan Xue
Yufan Xue
YSyu sun
yu sun
JZJiawei Zhou
Jiawei Zhou
LPLisha Peng
Lisha Peng
XZxianzhong zhou
xianzhong zhou
With the development of society, intelligent games have gradually become a hot research field. The paper proposes an algorithm that combines the multi-attribute decision-making and reinforcement learning methods to apply to multi-agents' decision-making for wargaming AI (artificial intelligence). This algorithm solves the problem of the agent's low rate of winning against specific rules and its inability to quickly converge during intelligent wargame training. At the same time, a multi-attribute decision-making method based on Entropy-Weight method was proposed to obtain the normalized weighting for each attribute that feeds into a deep reinforcement learning model. A simulation experiment confirms that the RNM-PPO (Real Number Multi-attribute decision-making-PPO) algorithm of multi-attribute decision-making combined with reinforcement learning presented in the paper is significantly more intelligent than the pure reinforcement learning algorithm.

22 November 2018 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
JDJie Ding
Jie Ding
JZJiawei Zhou
Jiawei Zhou
VTVahid Tarokh
Vahid Tarokh

28 December 2020 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
JDJie Ding
Jie Ding
EDEnmao Diao
Enmao Diao
JZJiawei Zhou
Jiawei Zhou
VTVahid Tarokh
Vahid Tarokh
A central issue of many statistical learning problems is to select an appropriate model from a set of candidate models. Large models tend to inflate the variance (or overfitting), while small models tend to cause biases (or underfitting) for a given fixed dataset. In this work, we address the critical challenge of model selection to strike a balance between model fitting and model complexity, thus gaining reliable predictive power. We consider the task of approaching the theoretical limit of statistical learning, meaning that the selected model has the predictive performance that is as good as the best possible model given a class of potentially misspecified candidate models. We propose a generalized notion of Takeuchi’s information criterion and prove that the proposed method can asymptotically achieve the optimal out-sample prediction loss under reasonable assumptions. It is the first proof of the asymptotic property of Takeuchi’s information criterion to our best knowledge. Our proof applies to a wide variety of nonlinear models, loss functions, and high dimensionality (in the sense that the models’ complexity can grow with sample size). The proposed method can be used as a computationally efficient surrogate for leave-one-out cross-validation. Moreover, for modeling streaming data, we propose an online algorithm that sequentially expands the model complexity to enhance selection stability and reduce computation cost. Experimental studies show that the proposed method has desirable predictive power and significantly less computational cost than some popular methods.

13 April 2026
Verified
Conference Paper
Open access
MRMonalika Padma Reddy
Monalika Padma Reddy
ABAruna Balasubramanian
Aruna Balasubramanian
JZJiawei Zhou
Jiawei Zhou
XBXiaojun Bi
Xiaojun Bi
IRIv Ramakrishnan
Iv Ramakrishnan
VAVikas Ashok
Vikas Ashok
AI tools like ChatGPT and Be-My-AI are increasingly being used by blind individuals. Although prior work has explored their use in some Do-It-Yourself (DIY) tasks by blind individuals, little is known about how they use these tools and the available product-manual resources to assemble, operate, and troubleshoot physical/tangible products – tasks requiring spatial reasoning, structural understanding, and precise execution. We address this knowledge gap via an interview study and a usability study with blind participants, investigating how they leverage AI tools and product manuals for DIY tasks with physical products. Findings show that manuals are essential resources, but product-manual instructions are often inadequate for blind users. AI tools presently do not adequately address this insufficiency, in fact, we observed that they often exacerbate this issue with incomplete, incoherent, or misleading guidance. Lastly, we suggest improvements to AI tools for generating tailored instructions for blind users’ DIY tasks involving tangible products.