Dai Zhongxiang
I'm a Research Fellow in Department of Computer Science, National University of Singapore.
I work on AI/machine learning, advised by Assoc. Prof. Bryan Kian Hsiang Low from NUS and Prof. Patrick Jaillet from MIT.
I'm interested in sequential decision-making under uncertainty problems, including Bayesian optimization, multi-armed bandits and reinforcement learning,
as well as their applications in AI for Science and autoML.
Previously, I also worked on computational neuroscience.
Email  / 
Google Scholar  / 
Twitter  / 
Github
|
|
What's New
-
Jan 2023: 2 papers accepted to ICLR 2023!
-
Dec 2022: Invited to serve as a reviewer for ICML 2023 and UAI 2023
-
Dec 2022: our paper on Recursive Reasoning-Based Training-Time Adversarial ML accepted to the AI Journal!
-
Sep 2022: 2 papers accepted to NeurIPS 2022!
-
Aug 2022: Invited to serve as a reviewer for AAMAS 2023
-
Aug 2022: Invited to serve as a reviewer for AAAI 2023
-
Jul 2022: Invited to serve as a reviewer for ICLR 2023
-
Jul 2022: Invited to serve as a reviewer for CoRL 2022
-
May 2022: Our papers on "Meta-Bayesian Optimization" and "Neural Ensemble Search" are accepted to UAI 2022!
-
May 2022: Our paper "Bayesian Optimization under Stochastic Delayed Feedback" accepted to ICML 2022!
-
Mar 2022: Invited to serve as a reviewer for NeurIPS 2022
-
Feb 2022: Invited to serve as a reviewer for Transactions on Machine Learning Research (TMLR)
-
Jan 2022: Our paper on NAS at Initialization accepted to ICLR 2022!
|
Education
-
National University of Singapore (NUS)   (Aug 2017 - Apr 2021)
-
National University of Singapore (NUS)   (Aug 2011 - Jun 2015)
-
Bachelor of Engineering (Electrical Engineering), First Class Honors
|
Publications
* denotes equal contribution, † denotes corresponding author.
-
Federated Neural Bandits.
Zhongxiang Dai, Yao Shu, Arun Verma, Flint Xiaofeng Fan, Kian Hsiang Low and Patrick Jaillet.
ICLR 2023. Acceptance rate: 31.8%.
-
Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation.
Yao Shu*, Zhongxiang Dai*, Weicong Sng, Arun Verma, Patrick Jaillet and Kian Hsiang Low.
ICLR 2023. Acceptance rate: 31.8%.
-
Recursive Reasoning-Based Training-Time Adversarial Machine Learning.
Yizhou Chen, Zhongxiang Dai, Haibin Yu, Kian Hsiang Low and Teck-Hua Ho.
In Artificial Intelligence (Special Issue on Risk-Aware Autonomous Systems: Theory and Practice), 2023.
-
Sample-Then-Optimize Batch Neural Thompson Sampling.
Zhongxiang Dai, Yao Shu, Kian Hsiang Low and Patrick Jaillet.
NeurIPS 2022. Acceptance rate: 25.6%. [arXiv, Code]
-
Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search.
Yao Shu, Zhongxiang Dai†, Zhaoxuan Wu and Kian Hsiang Low.
NeurIPS 2022. Acceptance rate: 25.6%. [arXiv]
-
Bayesian Optimization under Stochastic Delayed Feedback.
Arun Verma*, Zhongxiang Dai* and Kian Hsiang Low.
ICML 2022. Acceptance rate: 21.9%.
-
On Provably Robust Meta-Bayesian Optimization.
Zhongxiang Dai, Yizhou Chen, Haibin Yu, Kian Hsiang Low and Patrick Jaillet.
UAI 2022. Acceptance rate: 32.3%. [OpenReview]
-
Neural Ensemble Search via Bayesian Sampling.
Yao Shu, Yizhou Chen, Zhongxiang Dai and Kian Hsiang Low.
UAI 2022. Acceptance rate: 32.3%. [OpenReview]
-
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization.
Yao Shu, Shaofeng Cai, Zhongxiang Dai, Beng Chin Ooi and Kian Hsiang Low.
ICLR 2022. Acceptance rate: 32.3%. [OpenReview, arXiv]
-
Differentially Private Federated Bayesian Optimization with Distributed Exploration.
Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
NeurIPS 2021. Acceptance rate: 26%. [OpenReview, Code]
-
Optimizing Conditional Value-At-Risk of Black-Box Functions.
Quoc Phong Nguyen, Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
NeurIPS 2021. Acceptance rate: 26%. [OpenReview, Code]
-
Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee.
Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Wei Jing, Cheston Tan and Kian Hsiang Low.
NeurIPS 2021. Acceptance rate: 26%. [OpenReview, Code]
-
Value-at-Risk Optimization with Gaussian Processes.
Quoc Phong Nguyen, Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
ICML 2021. Acceptance rate: 21.4%. [Proceedings, Code]
-
Federated Bayesian Optimization via Thompson Sampling.
Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
NeurIPS 2020. Acceptance rate: 20.1%. [Code, Proceedings]
-
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games.
Zhongxiang Dai, Yizhou Chen, Kian Hsiang Low, Patrick Jaillet and Teck-Hua Ho.
ICML 2020. Acceptance rate: 21.8%. [Code, Proceedings, Video]
-
Private Outsourced Bayesian Optimization.
Dmitrii Kharkovskii, Zhongxiang Dai and Kian Hsiang Low.
ICML 2020. Acceptance rate: 21.8%. [Code, Proceedings, Video]
-
Bayesian Optimization Meets Bayesian Optimal Stopping.
Zhongxiang Dai, Haibin Yu, Kian Hsiang Low, and Patrick Jaillet.
ICML 2019. Acceptance rate: 22.6%. [Code, Proceedings]
-
Bayesian Optimization with Binary Auxiliary Information.
Yehong Zhang, Zhongxiang Dai, and Kian Hsiang Low.
UAI 2019. Acceptance rate: 26.2% (plenary talk). [Code]
-
Implicit Posterior Variational Inference for Deep Gaussian Processes.
Haibin Yu*, Yizhou Chen*, Zhongxiang Dai, Kian Hsiang Low, and Patrick Jaillet.
NeurIPS 2019. Acceptance rate: 3% (spotlight). [Code]
|
Awards and Honors
-
Dean's Graduate Research Excellence Award, NUS, School of Computing, 2021
-
Research Achievement Award × 2, NUS, School of Computing, 2019 & 2020
-
Singapore-MIT Alliance for Research and Technology (SMART) Graduate Fellowship, Aug 2017
-
JDDiscovery Population Dynamics Census and Prediction Competition 2018 (annual competition hosted by JD.com): global champion,
ranked 1st among > 2,100 teams, Jan 2019 (News in English, News in Chinese)
-
ST Electronics Prize × 2 (the top student in the cohort of Electrical Engineering Year 1 & 2, NUS), Academic Year
2011/2012 & 2012/2013
-
Dean’s List × 5 (top 5% in Electrical Engineering, NUS), 2011-2015
-
Singapore Ministry of Education SM3 scholarship for undergraduate PRC students, 2010
|
Professional Services
-
Senior Program Committee (SPC) member of IJCAI 2021, Program Committee Board member of IJCAI 2022-2024
-
Program Committee (PC) member/reviewer of
-
ICML (2021, 2022, 2023)
-
NeurIPS (2020, 2021, 2022)
-
ICLR (2021, 2022, 2023)
-
UAI (2023)
-
AISTATS (2023)
-
AAAI (2021, 2022, 2023)
-
CoRL (2020, 2021, 2022)
-
CVPR (2021, 2022)
-
ICCV (2021)
-
AAMAS (2023)
-
IROS (2021)
-
ICRA (2022)
-
Journal reviewer for
-
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
-
Transactions on Machine Learning Research (TMLR)
-
IEEE Robotics and Automation Letters (RA-L)
|
Academic Talks
-
Bayesian Optimization Meets Bayesian Optimal Stopping, at Singapore-MIT Alliance, Future Urban Mobility Symposium 2019, Jan 28, 2019.
-
Bayesian Optimization Meets Bayesian Optimal Stopping, at Learning and Vision Lab Group Seminar, NUS, ECE, Mar 8, 2019.
-
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games, at NUS Computing Research Week 2020, Aug 4, 2020 (top 3 student presenter).
|
Teaching
-
Tutor for CS3244 Machine Learning, NUS School of Computing (Spring 2019)
-
Teaching Assistant for CS1010E Programming Methodology, NUS School of Computing (3 semesters from 2012 to 2014)
|
|