I completed a Ph.D. in Computer Science at Boston University, where I was advised by Alina Ene. Prior to that, I obtained my Master's and Bachelor's degrees from the National University of Singapore, where I worked with Yair Zick. I also earned the Diplôme d'Ingénieur from École Polytechnique.

My research interests span Optimization, Machine Learning and Theoretical Computer Science.

Contact: taduy at bu dot edu

Conference papers

1. Solving Positive Linear Programs with Differential Privacy

   (\(\alpha\beta\)) Alina Ene, Huy Le Nguyen, Ta Duy Nguyen, Adrian Vladu

   In Proceedings of the 42th International Conference on Machine Learning (ICML 2026). [pdf]

2. Improved \(\ell_p\)-Regression via Iteratively Reweighted Least Squares

   (\(\alpha\beta\)) Alina Ene, Ta Duy Nguyen, Adrian Vladu

   In Proceedings of the 11th International Conference on Learning Representations (ICLR 2026). [pdf]

3. Quasi-Self-Concordant Optimization with \(\ell_{\infty}\) Lewis Weights

   (\(\alpha\beta\)) Alina Ene, Ta Duy Nguyen, Adrian Vladu

   In Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025). [pdf]

4. Solving Linear Programs with Differential Privacy

   (\(\alpha\beta\)) Alina Ene, Huy Le Nguyen, Ta Duy Nguyen, Adrian Vladu

   In Proceedings of the 2025 International Conference on Randomization and Computation (RANDOM 2025). [pdf]

5. Multiplicative Weights Update, Area Convexity and Random Coordinate Descent for Densest Subgraph Problems

   Ta Duy Nguyen, Alina Ene

   In Proceedings of the 40th International Conference on Machine Learning (ICML 2024) (Oral Presentation). [pdf]

6. On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis

   Ta Duy Nguyen, Alina Ene, Huy Le Nguyen

   In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023).

7. Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise

   Ta Duy Nguyen*, Thien Hang Nguyen*, Alina Ene, Huy Le Nguyen

   In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023) (Spotlight).

   This paper is a merger of two preprints [arxiv:2302.05437] and [arxiv:2304.01119].

8. High Probability Convergence of Stochastic Gradient Methods

   Zijian Liu*, Ta Duy Nguyen*, Thien Hang Nguyen*, Alina Ene, Huy Le Nguyen

   In Proceedings of the 40th International Conference on Machine Learning (ICML 2023). [pdf]

9. On the Convergence of AdaGrad on \(\mathbb{R}^{d}\): Beyond Convexity, Non-Asymptotic Rate and Acceleration

   Zijian Liu*, Ta Duy Nguyen*, Alina Ene, Huy Le Nguyen

   In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023). [pdf]

10. Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction

    Zijian Liu*, Ta Duy Nguyen*, Alina Ene, Huy Le Nguyen

    In Proceedings of the 39th International Conference on Machine Learning (ICML 2022). [pdf]

11. Threshold Task Games: Theory, Platform and Experiments

    (\(\alpha\beta\)) Kobi Gal, Ta Duy Nguyen, Quang Nhat Tran, Yair Zick

    In Proceedings of the 19th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2020). [pdf]

12. Resource Based Cooperative Games: Optimization, Fairness and Stability

    (\(\alpha\beta\)) Ta Duy Nguyen, Yair Zick

    In Proceedings of the 11th International Symposium on Algorithmic Game Theory (SAGT 2018) (Short paper). [pdf]

13. Fast Genetic Algorithms

    (\(\alpha\beta\)) Benjamin Doerr, Huu Phuoc Le, Regis Makhmara, Ta Duy Nguyen

    In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2017). [pdf]

Manuscripts

1. META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions

   Zijian Liu*, Ta Duy Nguyen*, Thien Hang Nguyen*, Alina Ene, Huy Le Nguyen

   [pdf]

2. On Adversarial Bias and the Robustness of Fair Machine Learning

   Hongyan Chang*, Ta Duy Nguyen*, Sasi Kumar Murakonda, Ehsan Kazemi, Reza Shokri

   [pdf]