I am Ruomin Huang (黄若民 in Chinese), a 1st-year CS Ph.D. student at Duke University. I am fortunate to be advised by Prof. Rong Ge. Previously I received M.S. in Data Science and B.S. in Computational Mathematics from USTC, where I worked with Prof. Hu Ding.

Research

Previously I worked on the algorithmic aspect of ML. Recently I am interested in the mechanism of in-context learning.

Publications

* denotes equal contribution.

• Ruomin Huang, Rong Ge, Task Descriptors Help Transformers Learn Linear Models In-Context, ICML 2024 Workshop on In-Context Learning.

• Roy Xie, Junlin Wang, Ruomin Huang, Minxing Zhang, Rong Ge, Jian Pei, Neil Gong, Bhuwan Dhingra, ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods, preprint.

• Weichen Lin*, Jiaxiang Chen*, Ruomin Huang, Hu Ding, An Effective Dynamic Gradient Calibration Method for Continual Learning, ICML 2024.

• Hu Ding, Ruomin Huang, Kai Liu, Haikuo Yu, Zixiu Wang, Randomized Greedy Algorithms and Composable Coreset for k-Center Clustering with Outliers, preprint.

• Ruomin Huang, Jiawei Huang, Wenjie Liu, Hu Ding, Coresets for Wasserstein Distributionally Robust Optimization Problems, NeurIPS 2022 (spotlight).

• Jiaxiang Chen, Qingyuan Yang, Ruomin Huang, Hu Ding, Coresets for Relational Data and The Applications, NeurIPS 2022 (spotlight).

• Jiawei Huang*, Ruomin Huang*, Wenjie Liu*, Nikolaos M. Freris, Hu Ding, A Novel Sequential Coreset Method for Gradient Descent Algorithms, ICML 2021 (spotlight).

Teaching Assistant

Undergraduate course

• 01118601 Algorithms for Big Data (2021 spring, USTC)
• COMPSCI 330 Design and Analysis of Algorithms (2024 spring, Duke)

Doctoral course

• COMP7102P01 Advanced Algorithms Design and Analysis (2021 fall, USTC)

Seminar

I am open to discussions.

• Feature Learning Seminar (2022 spring) on papers:
  • the Tensor Program series, by Greg Yang, et al.
• High-Dimensional Statistics Seminar (2021 fall) on books:
  • High-Dimensional Statistics: A Non-Asymptotic Viewpoint, by Martin J. Wainwright.
  • High-Dimensional Probability: An Introduction with Applications in Data Science, by Roman Vershynin.
• Spectral and Algebraic Graph Seminar (2021 fall) on the note:
  • Spectral and Algebraic Graph Theory, by Daniel A. Spielman.