Viet Anh NGUYEN
 |
Viet Anh Nguyen |
News
May 2024: Some new papers:
Small Sample Behavior of Wasserstein Projections, Connections to Empirical Likelihood, and Other Applications, with Sirui Lin, Jose Blanchet, and Peter Glynn.
A Geometric Unification of Distributionally Robust Covariance Estimators: Shrinking the Spectrum by Inflating the Ambiguity Set, with Man-Chung Yue, Yves Rychener, and Daniel Kuhn.
Cold-start Recommendation by Personalized Embedding Region Elicitation, with Hieu Nguyen, Duy Nguyen, and Khoa Doan. UAI 2024.
Generative Conditional Distributions by Neural (Entropic) Optimal Transport, with Bao Nguyen, Binh Nguyen, and Hieu Nguyen. ICML 2024.
Explaining Graph Neural Networks via Structure-aware Interaction Index, with Ngoc Bui, Hieu Nguyen, and Rex Ying. ICML 2024.
April 2024: Haodong Hu won the CEFAR Academy gold medal. Haodong delivered a privacy-preserving, environmental-friendly, and fact-based generative AI solution for anti-money laundering in Hong Kong!
March 2024: Two new papers:
Bellman Optimal Step-size Straightening of Flow-Matching Models, with Bao Nguyen and Binh Nguyen. ICLR 2024.
Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitation, with Duy Nguyen and Bao Nguyen.
August 2023: The CUHK team is collaborating with VinUniversity and the Hanoi Obstetrics & Gynecology Hospital to develop the next generation of gynecological care, funded by the Grand Challenges: Catalyzing Equitable Artificial Intelligence (AI) Use Challenge Awards.
Recruitment
I am recruiting junior researchers at all ranks (undergraduate/Master's/Ph.D. students, postdoctoral fellows or research assistants) working at the Chinese University of Hong Kong. The research areas of interest include ethical analytics, responsible AI, human-machine interactions, robustness, etc. The start date is flexible and the remuneration is attractive. To apply, please fill up this Google form or send your application package to my email address.
For prospective Ph.D. students, please consult the Ph.D. program leaflet and the Hong Kong PhD Fellowship Scheme leaflet.
Biography
Viet Anh Nguyen is currently an Assistant Professor at the Department of Systems Engineering and Engineering Management, the Chinese University of Hong Kong.
From 2019 until summer 2021, Viet Anh Nguyen was a postdoctoral researcher at Stanford University, working with Professor Jose Blanchet and Professor Yinyu Ye. Between summer 2021 and summer 2022, he was a research scientist, leading the Machine Learning and Deep Learning research group at VinAI Research, Vietnam.
Viet Anh Nguyen received his doctoral degree in Management of Technology from Ecole Polytechnique Federale de Lausanne in 2019, where he worked with Daniel Kuhn and Peyman Mohajerin-Esfahani.
He received a Bachelor of Engineering and a Master of Engineering in Industrial and Systems Engineering from the National University of Singapore in 2011 and 2013 respectively. He also holds a Diplome d'Ingenieur (promotion Gustave Eiffel) from Ecole Centrale des Arts et Manufactures (Ecole Centrale de Paris). He graduated from the Swiss Program for Beginning Doctoral Students in Economics at the Study Center Gerzensee in 2014. He is interested in very large-scale decision making under uncertainty, statistical optimization and machine learning with applications in energy systems, operations management, and data/policy analytics.
Publications
Journal Publications
Robustifying Conditional Portfolio Decisions via Optimal Transport, with Fan Zhang, Shanshan Wang, Jose Blanchet, Erick Delage and Yinyu Ye. Operations Research, 2024.
Wassestein Robust Classification with Fairness Constraints, with Yijie Wang and Grani Hanasusanto. Manufacturing & Service Operations Management, 2024.
Machine Learning's Dropout Training is Distributionally Robust Optimal, with Jose Blanchet, Yang Kang, Jose Luis Montiel Olea and Xuhui Zhang. Journal of Machine Learning Research, 2023.
Bridging Bayesian and Minimax Mean Square Error Estimation via Wasserstein Distributionally Robust Optimization, with Soroosh Shafiee, Daniel Kuhn and Peyman Mohajerin Esfahani. Mathematics of Operations Research, 2023. [Code].
Distributionally Robust Inverse Covariance Estimation: The Wasserstein Shrinkage Estimator, with Daniel Kuhn and Peyman Mohajerin Esfahani. Operations Research, 2020. [arXiv], [Code].
First place, George Nicholson Student Paper Competition, INFORMS 2018.
Energy and Reserve Dispatch with Distributionally Robust Joint Chance Constraints, with Christos Ordoudis, Daniel Kuhn and Pierre Pinson. Operations Research Letters, 2021. [Code].
A Linear-Quadratic Gaussian Approach to Dynamic Information Acquisition, with Thomas Weber. European Journal of Operational Research, 2018. [SSRN].
Satisficing Measure Approach for Vehicle Routing Problem with Time Windows under Uncertainty, with Jun Jiang, Kien Ming Ng and Kwong Meng Teo. European Journal of Operational Research, 2016.
Commuter Cycling Policy in Singapore: a Farecard Data Analytics based Approach, with Ashwani Kumar and Kwong Meng Teo. Annals of Operations Research, 2016.
Conference Publications
Generative Conditional Distributions by Neural (Entropic) Optimal Transport, with Bao Nguyen, Binh Nguyen, and Hieu Nguyen. ICML 2024.
Explaining Graph Neural Networks via Structure-aware Interaction Index, with Ngoc Bui, Hieu Nguyen, and Rex Ying. ICML 2024.
Cold-start Recommendation by Personalized Embedding Region Elicitation, with Hieu Nguyen, Duy Nguyen, and Khoa Doan. UAI 2024.
Bellman Optimal Step-size Straightening of Flow-Matching Models, with Bao Nguyen and Binh Nguyen. ICLR 2024.
Efficient Failure Pattern Identification of Predictive Algorithms, with Bao Nguyen. UAI 2023.
Dynamic Flows on Curved Space Generated by Labeled Data, with Xinru Hua, Truyen Nguyen, Tam Le, and Jose Blanchet. IJCAI 2023.
Distributionally Robust Recourse Action, with Duy Nguyen, and Ngoc Bui. ICLR 2023.
Honorable Mention. INFORMS 2022 Undergraduate Operations Research Prize.
Feasible Recourse Plan via Diverse Interpolation, with Duy Nguyen and Ngoc Bui. AISTATS 2023.
Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints, with Jiajin Li, Sirui Lin and Jose Blanchet. NeurIPS 2022.
Robust Bayesian Recourse, with Tuan-Duy H. Nguyen, Ngoc Bui, Duy Nguyen and Man-Chung Yue. UAI 2022.
Counterfactual Plans under Distributional Ambiguity, with Ngoc Bui and Duy Nguyen. ICLR 2022. [Code]
Distributionally Robust Fair Principal Components via Geodesic Descents, with Hieu Vu, Toan Tran and Man-Chung Yue. ICLR 2022. [Code]
Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics, with Tam Le, Truyen Nguyen and Dinh Phung. AISTATS 2022.
Human Imperceptible Attacks and Applications to Improve Fairness, with Xinru Hua, Huanzhong Xu and Jose Blanchet. Winter Simulation Conference 2022.
Adversarial Regression with Doubly Non-negative Weighting Matrices, with Tam Le, Truyen Nguyen, Makoto Yamada, Jose Blanchet. NeurIPS 2021.
Testing Group Fairness via Optimal Transport Projections, with Nian Si, Karthyek Murthy and Jose Blanchet. ICML 2021.
Principal Component Hierarchy for Sparse Quadratic Programs, with Robbie Vreugdenhil, Armin Eftekhari and Peyman Mohajerin Esfahani. ICML 2021. [Code]
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts, with Bahar Taskesen, Man-Chung Yue, Jose Blanchet and Daniel Kuhn. ICML 2021 (Oral presentation). [Code]
A Statistical Test for Probabilistic Fairness, with Bahar Taskesen, Jose Blanchet and Daniel Kuhn. ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2021. [Code]
Distributionally Robust Parametric Maximum Likelihood Estimation, with Xuhui Zhang, Jose Blanchet and Angelos Georghiou. NeurIPS 2020. [Code]
Distributionally Robust Local Non-parametric Conditional Estimation, with Fan Zhang, Jose Blanchet, Erick Delage and Yinyu Ye. NeurIPS 2020. [Code]
Robust Bayesian Classification Using an Optimistic Score Ratio, with Nian Si and Jose Blanchet. ICML 2020. [Code]
Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimization, with Soroosh Shafiee, Man-Chung Yue, Daniel Kuhn and Wolfram Wiesemann. NeurIPS 2019. [Code].
Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximation, with Soroosh Shafiee, Man-Chung Yue, Daniel Kuhn and Wolfram Wiesemann. NeurIPS 2019. [Code].
Wasserstein Distributionally Robust Kalman Filtering, with Soroosh Shafiee, Daniel Kuhn and Peyman Mohajerin Esfahani. NeurIPS 2018 (Spotlight). [arXiv], [Code].
Tutorials
Statistical Analysis of Wasserstein Distributionally Robust Estimators, with Jose Blanchet and Karthyek Murthy. INFORMS TutORials in Operations Research, 2021.
Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning, with Daniel Kuhn, Peyman Mohajerin Esfahani and Soroosh Shafiee. INFORMS TutORials in Operations Research, 2019. [Video].
Preprints
Small Sample Behavior of Wasserstein Projections, Connections to Empirical Likelihood, and Other Applications, with Sirui Lin, Jose Blanchet, and Peter Glynn. Under review.
A Geometric Unification of Distributionally Robust Covariance Estimators: Shrinking the Spectrum by Inflating the Ambiguity Set, with Man-Chung Yue, Yves Rychener, and Daniel Kuhn. Under review.
Wasserstein-based Minimax Estimation of Dependence in Multivariate Regularly Varying Extremes, with Xuhui Zhang, Jose Blanchet, Youssef Marzouk and Sven Wang. Under review.
Coverage-Validity-Aware Algorithmic Recourse, with Ngoc Bui, Duy Nguyen, and Man-Chung Yue. Under review.
Wasserstein Distributionally Robust Gaussian Process Regression and Linear Inverse Problems, with Xuhui Zhang, Jose Blanchet, Youssef Marzouk, and Sven Wang. Under review.
Bayesian Imputation with Optimal Look-Ahead-Bias and Variance Tradeoff, with Jose Blanchet, Fernando Hernandez, Markus Pelger, and Xuhui Zhang. Under review.
Mean-Covariance Robust Risk Measurement, with Soroosh Shafiee, Damir Filipovic, and Daniel Kuhn. Under review.
Forever Preprints
Below is a list of papers for which we do not have the resources to follow up with the reviewing process. They are all beautiful; I hope you enjoy reading these papers as much as I enjoy writing them!
Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitation, with Duy Nguyen and Bao Nguyen.
A Distributionally Robust Approach to Fair Classification, with Bahar Taskesen, Daniel Kuhn, and Jose Blanchet.
Errors are unavoidable. If you find any technical or implementation errors in our papers or codes, please email me to report them. Thank you!
Thesis
Adversarial Analytics. Ph.D. thesis at Ecole Polytechnique Federale de Lausanne. 2019.
Routing and Planning for The Last Mile Mobility System. Master thesis at National University of Singapore. 2012.
Awards & Scholarships
First place, George Nicholson Student Paper Competition, INFORMS 2018.
Best Teaching Assistant Award, Ecole Polytechnique Federale de Lausanne, 2018.
Teaching Assistantship, National University of Singapore, 2010-2012.
Eiffel Excellence Scholarship, 2008-2010.
ASEAN Undergraduate Scholarship, National University of Singapore, 2006-2010.
Current Team
Zikun Lin. PhD student at CUHK.
Yue Lin. PhD student at CUHK.
Hieu Nguyen. PhD student at CUHK.
Bao Nguyen. PhD student at CUHK.
Yilin Gu. PhD student at CUHK.
Dongxuan Zhu. PhD student at CUHK.
Wang Shanshan. Postdoctoral researcher at CUHK.
Former Research Students
Duy Nguyen. Research resident at VinAI Research. First position: CS PhD student at the University of North Carolina.
Marshal Sinaga. Research assistant at CUHK. Now: CS PhD student at Aalto University.
Austin Li. Research assistant at CUHK. Now: Econ PhD student at University College London.
Ngoc Bui. Research resident at VinAI Research. First position: CS PhD student at Yale University.
Tuan-Duy H. Nguyen. Research resident at VinAI Research. First position: CS PhD student at the National University of Singapore.
Hieu Vu. Research resident at VinAI Research. First position: CS PhD student at the University of Iowa.
Sirui Lin. PhD student at Stanford MS&E.
Xuhui Zhang. PhD student at Stanford MS&E.
Bahar Taskesen. PhD student at EPFL. Now at University of Chicago.
Andreas Bill. Master student at EPFL, 2017. Thesis title: Distributionally robust optimization of solar energy planning for Switzerland 2050.
Yves Rychener. Master student at EPFL, 2019. Project title: Distributionally robust shrinkage estimator.
Professional Service
Reviewer for journals: Management Science, Operations Research, Mathematical Programming, Mathematics of Operations Research, SIAM Journal on Optimization, INFORMS Journal on Computing, European Journal of Operational Research, Automatica, IEEE Transactions on Signal Processing, IEEE Transactions on Automatic Control, IEEE Transactions on Power Systems, Operations Research Letters, Transportation Research: Part B and Part E, Computers & Industrial Engineering, Journal of Optimization Theory and Applications, Expert Systems with Applications, Energy Systems, Computational Optimization and Applications.
Reviewer for conferences: SIAM SODA 2019, ACC 2019, IEEE CDC 2017, 2019, NeurIPS 2020, 2021, 2022, ICML 2021, 2022, 2023, ICLR 2021, 2022, 2023, FAccT 2022.
Area Chair for conferences: FAccT 2023, 2024, NeurIPS 2023, 2024.
Collaborators
Signature
 |
To Normality and Beyond! |