Thanh Nguyen-Tang

I am a Postdoctoral Research Fellow at Department of Computer Science, Whiting School of Engineering, Johns Hopkins University, working with Raman Arora. I was an Associate Research Fellow at the Applied AI Institute, Deakin University in July 2021-June 2022 and completed my PhD there in Feb 2022. I did my Master in Computer Science and Engineering at Ulsan National University of Science and Technology (UNIST) in 2018.

Research Interests

I am building toward data-efficient, deployment-efficient and trustworthy AI by studying three foundational pillars of modern machine learning - provable statistical efficiency, computational efficiency, and robustness. My current focus includes

• Reinforcement Learning

• Learning under Distributional Shifts

• Probabilistic Deep Learning

• Representation Learning

I’m always actively open to research collaborations and chat!

Here are my Google Scholar, Semantic Scholar, Github, Twitter .

Recent News

• Sep. 14, 2022: One paper got accepted to NeurIPS, 2022.

• Aug. 8, 2022: I am acknowledged in Mengyan Zhang's PhD thesis.

• Jan. 21, 2022: One paper got accepted to ICLR, 2022.

• Oct. 25, 2021: A short version of our work has been accepted to the NeurIPS’21 Workshop on Offline Reinforcement Learning.

• July 8, 2021: A short version of our work has been accepted to the ICML’21 Workshop on Reinforcement Learning Theory.

• July 1, 2021: I start my postdoc at A\(^2\)I\(^2\), Deakin University after submitting my Ph.D. thesis in 24 Jun.

• May 20, 2021: I have been accepted to the Deep Learning Theory Summer School at Princeton, acceptance rate: 180/500 = 36%.

Publications

2022

• Improving Domain Generalization with Interpolation Robustness
  

  • Ragja Palakkadavath, Thanh Nguyen-Tang, Sunil Gupta, Svetha Venkatesh
    

  • Distribution Shifts Workshop@NeurIPS2022, INTERPOLATE@NeurIPS2022 (Spotlight)
    

  • Under review, 2022
    

• Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards
  

  • Thanh Nguyen-Tang, Raman Arora
    

  • Under review, 2022
    

• On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation
  

  • Thanh Nguyen-Tang, Ming Yin, Sunil Gupta, Svetha Venkatesh, Raman Arora
    

  • Under review, 2022
    

• Learning Fractional White Noises in Neural Stochastic Differential Equations
  

  • Anh Tong, Thanh Nguyen-Tang, Toan Tran, Jaesik Choi
    

  • NeurIPS, 2022
    

• Two-Stage Neural Contextual Bandits for Adaptive Personalised Recommendation
  

  • Mengyan Zhang, Thanh Nguyen-Tang, Fangzhao Wu, Zhenyu He, Xing Xie, Cheng Soon Ong
    

  • Under review, 2022
    

  • [arXiv]

• Contextual Bandits with Reduced Explorations via Logged Data
  

  • Hung Tran-The, Thanh Nguyen-Tang, Sunil Gupta, Santu Rana, Svetha Venkatesh
    

  • Under review, 2022
    

• Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization
  

  • Thanh Nguyen-Tang, Sunil Gupta, A.Tuan Nguyen, and Svetha Venkatesh
    

  • ICLR, 2022
    

  • Workshop on Offline Reinforcement Learning, NeurIPS, 2021
    

  • [arXiv] [Poster] [Slides] [Code]

2021

• Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks
  

  • Thanh Nguyen-Tang, Sunil Gupta, Hung Tran-The, Svetha Venkatesh
    

  • Workshop on Reinforcement Learning Theory, ICML, 2021
    

  • [arXiv] [Slides] [Talk]

• Distributional Reinforcement Learning via Moment Matching
  

  • Thanh Nguyen-Tang, Sunil Gupta, Svetha Venkatesh
    

  • AAAI, 2021
    

  • [arXiv] [Code] [Slides] [Poster] [Talk]

2020

• Distributionally Robust Bayesian Quadrature Optimization
  

  • Thanh Tang Nguyen, Sunil Gupta, Huong Ha, Santu Rana, Svetha Venkatesh
    

  • AISTATS, 2020
    

  • [arXiv] [Code] [Slides] [Talk]

2019

• Markov Information Bottleneck to Improve Information Flow in Stochastic Neural Networks
  

  • Thanh Tang Nguyen, Jaesik Choi
    

  • Entropy, 21(10), 976, 2019
    

  • [Code]

• Bayesian Optimization with Unknown Search Space
  

  • Huong Ha, Santu Rana, Sunil Gupta, Thanh Tang Nguyen, Hung Tran-The, Svetha Venkatesh
    

  • NeurIPS, 2019
    

  • [Code] [Poster]

Dissertations

• On Practical Reinforcement Learning: Provable Robustness, Scalability and Statistical Efficiency
  

  • Ph.D. dissertation, Deakin University, Australia, July 2021

• Parametric Information Bottleneck to Optimize Stochastic Neural Networks
  

  • Master Thesis, Ulsan National University of Science and Technology, South Korea, 2018
    

  • [Slides] [Talk]

Academic Service

• Senior Program Committee: AAAI (2023)

• Reviewer/Program Committee: NeurIPS (2022, 2021, 2020), ICML (2022, 2021), ICLR (2023, 2022, 2021- Outstanding reviewer award), AISTATS (2021), AAAI (2022, 2021-Top 25% of Program Committees, 2020), EWRL (2022), L4DC (2022), NeurIPS Workshop on Offline Reinforcement Learning (2022, 2021)

• Volunteer: ICML (2022), AutoML (2022)