About Me
I am a PhD student in Department of Statistics, The Pennsylvania State University. I am fortunate to be advised by Professor Matthew Reimherr. Prior to this, I received my Bachelor degree in Statistics from University of Science and Technology of China.
My research interests are mainly forcing on statistical transfer learning, functional/longitudinal data and differential privacy with kernel methods. Currently, I’m interested in leveraging kernel methods to theoretically address learning problems with different types of distribution shifts.
Preprints
- Spectral Algorithms with Gaussian Kernels: Robustness and Optimality.
Haotian Lin and Matthew Reimherr
(Under Review)
Publication
-
Pure Differential Privacy for Functional Summaries via a Laplce-like Process.
Haotian Lin and Matthew Reimherr
To appear in Journal of Machine Learning Research (JMLR), 2024
[arXiv] -
Smoothness Adaptive Hypothesis Transfer Learning.
Haotian Lin and Matthew Reimherr
International Conference on Machine Learning (ICML), 2024
[arXiv] -
On Hypothesis Transfer Learning in Functional Linear Models.
Haotian Lin and Matthew Reimherr
International Conference on Machine Learning (ICML), 2024
[arXiv]