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, including Bayesian optimization, multi-armed bandit and reinforcement learning. Previously, I also worked on computational neuroscience.

Email  /  Google Scholar  /  Twitter  /  Github

• Sep 2021: Three papers accepted to NeurIPS 2021!

• Sep 2021: Invited to serve as a reviewer for IEEE RA-L and ICRA 2022

• Aug 2021: Won Dean's Graduate Research Excellence Award!

• Aug 2021: Invited to serve as a Program Committee member for AAAI 2022

• Jul 2021: Invited to serve as a Program Committee member for NeurIPS 2021 Workshop on Federated Learning

• Jul 2021: Invited to serve as a Program Committee Board member for IJCAI 2022-2024 (PC member for 3 years)

• Jul 2021: Invited to serve as a reviewer for CVPR 2022

• Jun 2021: Defended my thesis titled Sample-Efficient Automated Machine Learning with Bayesian Optimization!
  

• National University of Singapore (NUS)   (Aug 2017 - Apr 2021)
  • Ph.D. student in Artificial Intelligence, Department of Computer Science
  • Advisors: Bryan Kian Hsiang Low (NUS) & Patrick Jaillet (MIT)
  • Thesis title: Sample-Efficient Automated Machine Learning with Bayesian Optimization
  • Supported by Singapore-MIT Alliance for Research and Technology (SMART) Graduate Fellowship, eligible for co-supervision by an MIT faculty and research residency at MIT for up to six months
• National University of Singapore (NUS)   (Aug 2011 - Jun 2015)
  • Bachelor of Engineering (Electrical Engineering), First Class Honors

• NASI: Label- and Data-agnostic Neural Architecture Search at Initialization.
  Yao Shu, Shaofeng Cai, Zhongxiang Dai, Beng Chin Ooi and Kian Hsiang Low.
  Pre-print, 2021 [arXiv]
  Key Words: training-free neural architecture search, neural tangent kernel.

• Going Beyond Neural Architecture Search with Sampling-based Neural Ensemble Search.
  Yao Shu, Yizhou Chen, Zhongxiang Dai and Kian Hsiang Low.
  Pre-print, 2021 [arXiv]
  Key Words: neural ensemble search, neural architecture search.

2021

• Differentially Private Federated Bayesian Optimization with Distributed Exploration.
  Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
  In 35th Conference on Neural Information Processing Systems (NeurIPS-21), Dec 6-14, 2021.
  Acceptance rate: 26%.
  

• Optimizing Conditional Value-At-Risk of Black-Box Functions.
  Quoc Phong Nguyen, Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
  In 35th Conference on Neural Information Processing Systems (NeurIPS-21), Dec 6-14, 2021.
  Acceptance rate: 26%.
  

• Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee.
  Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Wei Jing, Cheston Tan and Kian Hsiang Low.
  In 35th Conference on Neural Information Processing Systems (NeurIPS-21), Dec 6-14, 2021.
  Acceptance rate: 26%.
  

• Value-at-Risk Optimization with Gaussian Processes.
  Quoc Phong Nguyen, Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
  In 38th International Conference on Machine Learning (ICML-21), Jun 18-24, 2021.
  Acceptance rate: 21.4%. [Proceedings]
  Key Words: value-at-risk, risk-averse optimization.

2020

• Federated Bayesian Optimization via Thompson Sampling.
  Zhongxiang Dai, Kian Hsiang Low and Patrick Jaillet.
  In 34th Conference on Neural Information Processing Systems (NeurIPS-20), Dec 6-12, 2020.
  Acceptance rate: 20.1%. [Code, Proceedings]
  Key Words: Bayesian optimization, federated learning, Thompson sampling.

• 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.
  In 37th International Conference on Machine Learning (ICML-20), Jul 12-18, 2020.
  Acceptance rate: 21.8%. [Code, Proceedings, Video]
  Key Words: Bayesian optimization, adversarial machine learning, multi-agent reinforcement learning, game theory.

• Private Outsourced Bayesian Optimization.
  Dmitrii Kharkovskii, Zhongxiang Dai and Kian Hsiang Low.
  In 37th International Conference on Machine Learning (ICML-20), Jul 12-18, 2020.
  Acceptance rate: 21.8%. [Code, Proceedings, Video]
  Key Words: Bayesian optimization, differential privacy.

2019

• Bayesian Optimization Meets Bayesian Optimal Stopping.
  Zhongxiang Dai, Haibin Yu, Kian Hsiang Low, and Patrick Jaillet.
  In 36th International Conference on Machine Learning (ICML-19), Long Beach, CA, Jun 9-15, 2019.
  Acceptance rate: 22.6%. [Code, Proceedings]
  Key Words: Bayesian optimization, early stopping, multi-fidelity, reinforcement learning, feature selection.

• Bayesian Optimization with Binary Auxiliary Information.
  Yehong Zhang, Zhongxiang Dai, and Kian Hsiang Low.
  In Conference on Uncertainty in Artificial Intelligence (UAI-19) , Tel Aviv, Israel, Jul 22-25, 2019.
  Acceptance rate: 26.2% (plenary talk). [Code]
  Key Words: Bayesian optimization, multi-fidelity, entropy search, reinforcement learning.

• Implicit Posterior Variational Inference for Deep Gaussian Processes.
  Haibin Yu*, Yizhou Chen*, Zhongxiang Dai, Kian Hsiang Low, and Patrick Jaillet.
  In 33th Conference on Neural Information Processing Systems (NeurIPS-19). Vancouver, Canada, Dec 7 - 12, 2019.
  Acceptance rate: 3% (spotlight). [Code]
  Key Words: deep Gaussian processes, generative adversarial networks, game theory.

• 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

• Senior Program Committee (SPC) member of IJCAI 2021, Program Committee Board member of IJCAI 2022-2024
• Program Committee (PC) member/reviewer of
• ICML (2021)
• NeurIPS (2020, 2021)
• ICLR (2021, 2022)
• AAAI (2021, 2022)
• CoRL (2020, 2021)
• CVPR (2021, 2022)
• ICCV (2021)
• IROS (2021)
• ICRA (2022)
• Journal reviewer of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and IEEE RA-L.

• 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).

• 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)