Thanh Nguyen-Tang

I am currently an Associate Research Fellow and was a PhD candidate of the Applied AI Institute at Deakin University. Prior to that, I was a researcher at Ulsan National University of Science and Technology (UNIST) from Mar 2018 to Dec 2019, and I obtained my Master at UNIST in 2018.

The goal of my research is to develop better understanding and tractable methods for learning and decision-making in modern practical settings with strong theoretical guarantees. My research interest lies at the intersection of machine learning with statistics and optimization. My research areas:

• Sequential decision-making under uncertainty (e.g., reinforcement learning, bandit, online learning),

• Robust generalization (e.g. OOD, adversarial learning)

• Statistical inference (e.g. semiparametric models and causal inference)

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

I created the “ML Theory Exchange Network” Discord channel (currently 66 members as of 25 Oct 2021) to connect ML-theory passionate self-learners (like myself) with senior researchers for exchanging ideas and learning resources.

I have been also serving as a ML technical consultant for a local startup company on NLP product solutions.

Latest News

• [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.

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

• [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

• 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]

• 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]

• 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

• Offline Contextual Bandit Learning under Support Defficiency
  Hung Tran-The, Thanh Nguyen-Tang, Sunil Gupta, Santu Rana, Svetha Venkatesh
  Under review, 2022

• Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks
  Thanh Nguyen-Tang, Sunil Gupta, Hung Tran-The, Svetha Venkatesh
  Under review, 2021

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]

Supervision and mentoring

• Ragja Palakkadavath, Ph.D. student in ML at A2I2, Deakin University – Topic: Domain Generalization – Role: Associate supervisor

• Qiyao Wei, senior undergrad at University of Toronto – Role: PhD application mentor

Academic Service

• Reviewer, L4DC, 2022

• Reviewer, ICML, 2022

• Program Committee, NeurIPS Workshop on Offline Reinforcement Learning, 2021

• Program Committee, AAAI, 2022

• Reviewer, ICLR, 2022

• Reviewer, NeurIPS, 2021

• Reviewer, ICML, 2021

• Reviewer, AISTATS, 2021

• Program Committee, AAAI, 2021

• Reviewer, ICLR, 2021 (outstanding reviewer award)

• Reviewer, NeurIPS, 2020