Assistant Professor
Education
- Ph.D. Statistics (2021), University of Chicago
- B.S. Mathematics (2016), Nanjing University
Expertise
- Statistics, Big Data
- Optimization
- Machine Learning
About
Sen Na is an Assistant Professor in the H. Milton Stewart School of Industrial and Systems Engineering (ISyE) at Georgia Tech. Prior to joining ISyE, he was a postdoctoral researcher in the Department of Statistics and the International Computer Science Institute (ICSI) at UC Berkeley, working with Michael W. Mahoney. He received his Ph.D. in statistics from the University of Chicago in 2021, under the supervision of Mihai Anitescu and Mladen Kolar. Before attending UChicago, he received his B.S. in mathematics from Nanjing University in 2016.
Dr. Na is broadly interested in the mathematical foundations of data science, with topics including high-dimensional statistics, graphical models, semiparametric models, optimal control, and large-scale and stochastic nonlinear optimization. He is also interested in the broad applications of machine learning methods in biology, neuroscience, and engineering.
Dr. Na has received multiple awards, including the prestigious William Rainey Harper Dissertation Fellowship from UChicago and the 2023 MAPR Meritorious Service Award from the Mathematical Optimization Society.
Research
My research is rooted in the mathematical foundations of data science, with primary focuses on high-dimensional statistics, computational statistics, nonlinear and nonconvex optimization, and control. My ultimate research goal is to develop next-generation stochastic numerical methods that exhibit promising statistical and computational efficiency in solving various problems in scientific machine learning. These problems include scalable and reliable energy systems, safe reinforcement learning, physics-informed networks, algorithmic fairness, diffusion models, and more.
Teaching
Many areas in statistics, machine learning, and operations research are inherently interdisciplinary and require strong foundations in mathematics and programming. To attract students to the research frontier, it is essential to establish a coherent training process that builds solid fundamentals, keeps engagement, and encourages intellectual breakthroughs. Such training should span a spectrum of levels, from foundational concepts in undergraduate courses to open-ended research challenges in graduate study, so as to present students with a clear and high-resolution picture of the field. As students specialize, they should develop a deep understanding of cutting-edge problems while retaining the ability to broaden their perspective, move across topics, and deploy diverse analytical tools. My goal as an educator is to articulate this picture and to inspire students to construct an even higher-resolution version through creative and critical thinking.
Representative Publications
1. Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming
Sen Na, Michael W. Mahoney
Journal of Machine Learning Research, 2025.
2. A Fast Temporal Decomposition Procedure for Long-horizon Nonlinear Dynamic Programming
Sen Na, Mihai Anitescu, Mladen Kolar
Mathematics of Operations Research, 2023.
3. Inequality Constrained Stochastic Nonlinear Optimization via Active-Set Sequential Quadratic Programming
Sen Na, Mihai Anitescu, Mladen Kolar
Mathematical Programming, 2023.
4. Superconvergence of Online Optimization for Model Predictive Control
Sen Na, Mihai Anitescu
IEEE Transactions on Automatic Control, 2023.
5. Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence
Sen Na, Michał Dereziński, Michael W. Mahoney
Mathematical Programming, 2022.
6. An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians
Sen Na, Mihai Anitescu, Mladen Kolar
Mathematical Programming, 2022.
7. Global Convergence of Online Optimization for Nonlinear Model Predictive Control
Sen Na
Advances in Neural Information Processing Systems, 2021.
8. High-dimensional Index Volatility Models via Stein's Identity
Sen Na, Mladen Kolar
Bernoulli, 2021.
9. Estimating Differential Latent Variable Graphical Models with Applications to Brain Connectivity
Sen Na, Mladen Kolar, Oluwasanmi Koyejo
Biometrika, 2020.
10. Exponential Decay in the Sensitivity Analysis of Nonlinear Dynamic Programming
Sen Na, Mihai Anitescu
SIAM Journal on Optimization, 2020.