Thanh Nguyen-Tang
Applied AI Institute (A\(^2\)I\(^2\))
Deakin University, Australia
Email: nguyent2792 [AT] gmail [DOC] com
I am currently a postdoctoral researcher of the Applied AI Institute at Deakin University.
Prior to that, I was a PhD student at Deakin University from Jan 2019 to Jul 2021,
was a researcher at Ulsan National University of Science and Technology (UNIST) from Mar 2018 to Dec 2019,
and obtained my Master at UNIST in 2018.
I work on machine learing with the goal of developing advanced data-driven machine learning and statistical methods for learning and reasoning in complex, structured models over large, structured datasets. In particular, I am interested in improving statistical efficiency and generalization beyond i.i.d. setting of machine and reinforcement learning systems via imposing/exploiting minimal structural inductive biases. Currently, I focus on: (i) (offline) RL theory (with neural function approximation), and (ii) robust generalization beyond i.i.d. setting, (iii) ML applications. See more at my research proposals.
I publish under Thanh Tang Nguyen (old name arrangement) and Thanh Nguyen-Tang (new one). Here are my latest CV, Google Scholar, Semantic Scholar, Github, Twitter .
Latest News
[Jul 8, 2021] A short version of our work have been accepted to the ICML Workshop on Reinforcement Learning Theory 2021.
[Jul 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
Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks
Thanh Nguyen-Tang, Sunil Gupta, Hung Tran-The, Svetha Venkatesh
ICML Workshop on Reinforcement Learning Theory, 2021
[arXiv] [Slides] [Talk]Distributional Reinforcement Learning via Moment Matching
Thanh Nguyen-Tang, Sunil Gupta, Svetha Venkatesh
AAAI, 2021
[arXiv] [Code] [Slides] [Poster] [Talk]Distributionally Robust Bayesian Quadrature Optimization
Thanh Tang Nguyen, Sunil Gupta, Huong Ha, Santu Rana, Svetha Venkatesh
AISTATS, 2020
[arXiv] [Code] [Slides] [Talk]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]
Preprints
Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support
Hung Tran-The, Sunil Gupta, Thanh Nguyen-Tang, Santu Rana, Svetha Venkatesh
Under review, 2021
Dissertations
On Practical Considerations of 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]
Services
Invited Reviewer/ Program Committee: NeurIPS’21 Workshop on Offline Reinforcement Learning, ICML (2021), NeurIPS (2020, 2021), ICLR (2021 - outstanding reviewer award, 2022), AAAI (2021, 2022), AISTATS (2021).