I am an AI Research Scientist at J.P.Morgan Chase AI Research.
My research interests lie in the intersection of machine learning, algorithmic game theory, and econometrics. I am particularly interested in online machine learning and exploration-exploitation tradeoffs, and their impact in socioeconomic environments. My current work focuses on bandit algorithms, differential privacy, federated learning, strategic learning, and uncertainty quantification.
I received a Ph.D. in Computer Science at the University of Minnesota, co-advised by Professors Steven Wu and Maria Gini. During my undergrad study, I received a B.S in Computer Science and Mathematics from Dickinson College, where I worked on a Genetic Algorithm honor project with Professor Grant Braught.
I am happy to talk about incentive-aware machine learning and uncertainty quantification. Feel free to contact me at tuandungngo207 [at] gmail.com
For more detail, please see my CV [CV]
Research
Adaptive and Robust Watermark for Generative Tabular Data [arxiv]
Daniel Ngo , Daniel Scott, Saheed Obitayo, Vamsi K. Potluru, Manuela Veloso
Reconciling Model Multiplicity for Downstream Decision Making [arxiv]
Ally Du, Daniel Ngo , Zhiwei Steven Wu
Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Exploration [arxiv]
Daniel Ngo, Keegan Harris, Anish Agarwal, Vasilis Syrgkanis, Zhiwei Steven Wu
Federated Learning as a Network Effects Game [arxiv]
Shengyuan Hu, Daniel Ngo, Shuran Zheng, Virginia Smith, Zhiwei Steven Wu
Incentivizing Combinatorial Bandit Exploration [arxiv]
Proceedings of the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
Xinyan Hu, Daniel Ngo, Aleksandrs Slivkins, Zhiwei Steven Wu
Improved Regret for Differentially Private Exploration in Linear MDP [arxiv]
Proceedings of the Thirty-ninth International Conference on Machine Learning (ICML 2022)
Daniel Ngo, Giuseppe Vietri, Zhiwei Steven Wu
Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses [arxiv]
Proceedings of the Thirty-ninth International Conference on Machine Learning (ICML 2022)
Keegan Harris, Daniel Ngo, Logan Stapleton, Hoda Heidari, Zhiwei Steven Wu
Incentivizing Compliance with Algorithmic Instruments [arxiv]
Proceedings of the Thirty-eighth International Conference on Machine Learning (ICML 2021)
Daniel Ngo, Logan Stapleton, Vasilis Syrgkanis, Zhiwei Steven Wu
Attentional autoencoder for weighted implicit collaborative filtering
Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems
Hoang-Vu Dang, Dung Ngo