HomeGoogle Scholar WebsiteSen Na: A Rising Star in Data Science and Optimization

Sen Na: A Rising Star in Data Science and Optimization

In the field of data science and optimization, one name that has been making waves is Sen Na. With a strong background in mathematics and statistics, Sen Na has emerged as a prominent researcher, known for his expertise in high-dimensional statistics, graphical models, semiparametric models, optimal control, and large-scale stochastic nonlinear optimization. Currently a postdoctoral researcher at the University of California, Berkeley, Sen Na is working with renowned data scientist Michael W. Mahoney. In this article, we will explore the remarkable journey and contributions of Sen Na in the world of data science and optimization.

Early Years and Education

Sen Na’s passion for mathematics and statistics started early in his life. He completed his undergraduate studies in mathematics from Nanjing University in 2016, where he laid the foundation for his future academic pursuits. During his time at Nanjing University, Sen Na’s exceptional aptitude for mathematics caught the attention of his professors, who recognized his potential for groundbreaking research.

Pursuing a Ph.D. in Statistics

Building upon his strong mathematical foundation, Sen Na pursued a Ph.D. in statistics at the University of Chicago, where he had the opportunity to work under the guidance of Mihai Anitescu and Mladen Kolar. It was during his time at the University of Chicago that Sen Na’s research interests began to take shape. He delved into various areas of data science, focusing on high-dimensional statistics, graphical models, and semiparametric models. Sen Na’s rigorous training and dedication to his research paved the way for significant contributions to the field.

Contributions to Data Science and Optimization

Graphical Models for Brain Connectivity

One notable area of Sen Na’s research is the estimation of differential latent variable graphical models with applications to brain connectivity. In collaboration with M. Kolar and O. Koyejo, Sen Na developed a novel approach to estimate graphical models that capture the underlying connections in brain networks. This research has the potential to enhance our understanding of brain function and neurological disorders.

Adaptive Stochastic Sequential Quadratic Programming

Sen Na’s expertise also extends to optimization methods. In collaboration with M. Anitescu and M. Kolar, Sen Na proposed an adaptive stochastic sequential quadratic programming approach. This method combines stochastic optimization techniques with quadratic programming to solve complex optimization problems efficiently and accurately. The development of this approach has broad implications across various domains, including engineering and economics.

Behavior-Aware Recommendation Systems

Another area of Sen Na’s research focuses on behavior-aware recommendation systems. In collaboration with M. Ma, H. Wang, C. Chen, and J. Xu, Sen Na developed a graph-based recommendation approach for interactive news. By considering user behavior and preferences, this system provides personalized recommendations, enhancing the user experience and engagement with news content.

Machine Learning in Biology and Neuroscience

Sen Na’s expertise in machine learning has also found application in biology and neuroscience. In collaboration with M. Ma, X. Zhang, C. Chen, and J. Xu, Sen Na developed a self-feature-based graph autoencoder model for miRNA-disease association prediction. This model leverages the power of machine learning to uncover potential relationships between microRNAs and diseases, aiding in disease diagnosis and treatment.

Current Research and Future Prospects

As a rising star in data science and optimization, Sen Na continues to push the boundaries of knowledge in his field. His current research focuses on topics such as nonlinear dynamic programming, online optimization, and large-scale statistical inference. Sen Na’s innovative approaches and deep understanding of mathematical foundations have garnered attention from the academic community and industry professionals alike.

Google Scholar
An adaptive stochastic sequential quadratic programming with differentiable exact augmented lagrangians

S Na, M Anitescu, M Kolar
Mathematical Programming, 1-71
27 2022
Estimating differential latent variable graphical models with applications to brain connectivity

S Na, M Kolar, O Koyejo
Biometrika 108 (2), 425-442
23 2021
The graph-based behavior-aware recommendation for interactive news

M Ma, S Na, H Wang, C Chen, J Xu
Applied Intelligence 52 (2), 1913-1929
21 2022
AEGCN: An autoencoder-constrained graph convolutional network

M Ma, S Na, H Wang
Neurocomputing 432, 21-31
19 2021
On the Convergence of Overlapping Schwarz Decomposition for Nonlinear Optimal Control

S Na, S Shin, M Anitescu, VM Zavala
IEEE Transactions on Automatic Control
19 2020
High-dimensional Varying Index Coefficient Models via Stein’s Identity.

S Na, Z Yang, Z Wang, M Kolar
J. Mach. Learn. Res. 20, 152:1-152:44
18 2019
Inequality constrained stochastic nonlinear optimization via active-set sequential quadratic programming

S Na, M Anitescu, M Kolar
Mathematical Programming, 1-75
16 2023
Exponential decay in the sensitivity analysis of nonlinear dynamic programming

S Na, M Anitescu
SIAM Journal on Optimization 30 (2), 1527-1554
13 2020
High-dimensional index volatility models via stein’s identity

S Na, M Kolar
Bernoulli 27 (2), 794-817
11 2021
Superconvergence of online optimization for model predictive control

S Na, M Anitescu
IEEE Transactions on Automatic Control
10 2020
Hessian averaging in stochastic Newton methods achieves superlinear convergence

S Na, M Dereziński, MW Mahoney
Mathematical Programming 201 (1), 473-520
9 2023
SFGAE: a self-feature-based graph autoencoder model for miRNA–disease associations prediction

M Ma, S Na, X Zhang, C Chen, J Xu
Briefings in Bioinformatics 23 (5), bbac340
7 2022
Asymptotic convergence rate and statistical inference for stochastic sequential quadratic programming

S Na, MW Mahoney
arXiv preprint arXiv:2205.13687
7 2022
Semiparametric nonlinear bipartite graph representation learning with provable guarantees

S Na, Y Luo, Z Yang, Z Wang, M Kolar
International Conference on Machine Learning, 7141-7152
7 2020
Convergence Analysis of Accelerated Stochastic Gradient Descent under the Growth Condition

YL Chen, S Na, M Kolar
To appear in Mathematics of Operations Research
6* 2021
A fast temporal decomposition procedure for long-horizon nonlinear dynamic programming

S Na, M Anitescu, M Kolar
Mathematics of Operations Research
6 2021
Global Convergence of Online Optimization for Nonlinear Model Predictive Control

S Na
35th Conference on Neural Information Processing Systems
5 2021
Sparse learning with semi-proximal-based strictly contractive Peaceman-Rachford splitting method

S Na, CJ Hsieh
arXiv preprint arXiv:1612.09357
4 2016
Fully stochastic trust-region sequential quadratic programming for equality-constrained optimization problems

Y Fang, S Na, MW Mahoney, M Kolar
arXiv preprint arXiv:2211.15943
3 2022
Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching

I Hong, S Na, MW Mahoney, M Kolar
40th International Conference on Machine Learning


Sen Na’s journey from an undergraduate student in mathematics to a renowned researcher in data science and optimization is truly remarkable. With his impressive contributions to high-dimensional statistics, graphical models, optimization methods, and machine learning applications, Sen Na has established himself as a prominent figure in the field. As he continues to explore new avenues of research, there is no doubt that Sen Na’s work will shape the future of data science and optimization, leaving a lasting impact on these rapidly evolving disciplines.

Additional Information

  • Sen Na is currently on the job market for the 2023-2024 academic year.
  • His research has been published in prestigious journals such as Mathematical Programming, Biometrika, and IEEE Transactions on Automatic Control.
  • Sen Na has collaborated with esteemed researchers and institutions, including the University of California, Berkeley, and the University of Chicago.
  • His work has been presented at conferences such as the Conference on Neural Information Processing Systems and the International Conference on Machine Learning.

Latest post