people

---

layout: about title: About permalink: / subtitle: Electrical and Computer Engineering, UIUC.

profile: align: right image: SeiyunShin_Profile2.jpg image_circular: false # crops the image to make it circular more_info: > Email: seiyuns2 at illinois dot edu <p>323 Coordinated Science Laboratory / 3405 Siebel Center for Computer Science </p> <p>1308 W Main Street MC 228 / 201 North Goodwin Avenue MC 258</p> <p>Urbana, IL, 61801</p>

news: true # includes a list of news items latest_posts: false # includes a list of the newest posts selected_papers: true # includes a list of papers marked as “selected={true}” social: true # includes social icons at the bottom of the page —

Hello everyone! I am a Ph.D. student in the ECE department at the University of Illinois Urbana Champaign, where I am fortunate to be co-advised by Prof. Ilan Shomorony and Prof. Han Zhao. My research is partly supported by Kwanjeong Educational Foundation Fellowship and Mavis Future Faculty Fellow from UIUC. Prior to joining UIUC, I received my M.S. degree from the department of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST), where I studied information theory under the supervision of Prof. Changho Suh. I graduated Summa Cum Laude, earning B.S. degrees in Electrical Engineering and Mathematics (double-major) from KAIST.

In the Fall 2024, I had the privilege of being a visiting graduate student in the Computer Science department at Umass Amherst, where I have worked under the guidance of Prof. Cameron Musco.

Earlier in my career, I also gained research experience at the Electronics and Telecommunications Research Institute (ETRI), a government-funded research institute in South Korea, as part of my mandatory military service.

Research Interests

I seek to gain insight into fundamental problems that are practically relevant. My research interests lie at the intersection of theoretical machine learning, algorithm design, information theory, and randomized numerical linear algebra, with the overarching goal of advancing our understanding of learning limits and developing efficient algorithms.

Specifically, I have been developing scalable algorithms and establishing theoretical guarantees on approximation and sample complexity, in (1) inference and learning from graph-structured data (with the use of graph neural networks and dynamic graph clustering), (2) privacy-preserving covariance estimation and regression, and (3) effective data attribution methods to ensure transparency and accountability in machine learning models, focusing on reliably tracing data contributions and building attributable AI frameworks.

Moving forward, I aim to study deep learning theory and high-dimensional statistics to broaden my research to include: (1) efficient model pruning to deploy resource-friendly models without significant loss in predictive power, (2) extending privacy-preserving frameworks to ensure security while maintaining performance in deep learning (3) addressing the impact of distributional shifts on model robustness and reliability.

Hello everyone! I am a Ph.D. student in the ECE department at University of Illinois Urbana Champaign. I am under the supervision of Prof. Ilan Shomorony and Prof. Han Zhao. My research is partly supported by Kwanjeong Educational Foundation Fellowship and Mavis Future Faculty Fellow from UIUC. Prior to joining UIUC, I received my M.S. degree from the department of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST). I studied information theory under the supervision of Prof. Changho Suh. I also graduated Summa Cum Laude, earning B.S. degrees in Electrical Engineering and Mathematics (double-major) from KAIST.

I also spent time in Electronics and Telecommunications Research Institute (ETRI), a government-funded research institute in South Korea, as part of my mandatory military service.

Research Interests

I seek to gain insight into fundamental problems that are practically relevant. My research interests lie at the intersection of theoretical machine learning, algorithm design, information theory, and randomized numerical linear algebra, with the overarching goal of advancing our understanding of learning limits and developing efficient algorithms.

Specifically, I have been developing scalable algorithms and establishing theoretical guarantees on approximation and sample complexity, in (1) inference and learning from graph-structured data (with the use of graph neural networks and dynamic graph clustering), (2) privacy-preserving covariance estimation and regression, and (3) effective data attribution methods to ensure transparency and accountability in machine learning models, focusing on reliably tracing data contributions and building attributable AI frameworks.

Moving forward, I aim to study deep learning theory and high-dimensional statistics to broaden my research to include: (1) efficient model pruning to deploy resource-friendly models without significant loss in predictive power, (2) extending privacy-preserving frameworks to ensure security while maintaining performance in deep learning (3) addressing the impact of distributional shifts on model robustness and reliability.