Huan He
Huan He, Postdoctoral fellow at University of Pennsylvania,
Email: Huan.He@Pennmedicine.upenn.edu
Gmail: hehuannb@gmail.com
[Google Scholar][Curriculem Vitae]
I am on the academic job market 2023-2024! Please reach out to me if you find my expertise and research align with your department.
My current research includes but is not limited to the following topics:
Efficient training algorithms (e.g., parallel computing, optimization, numerical analysis)
Transfer learning (e.g., domain adaptation/generalization)
Trustworthy learning (e.g., short-cut learning, calibration, robustness)
Deep generative model for graph-structured data (e.g., transaction networks, social networks, 3D molecular conformation)
News
[Jan-2024] “A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality” is accepted by ICLR’24!
[June-2023] Check out our new preprint on explainable ML for time series TimeX!
[June-2023] Check out our new preprint on novel efficient nonlinear acceleration nlTGCR!
[Apr-2023] “Raincoat: Time Series Domain Adaptation under feature and label shifts” is accepted by ICML’23!
[Feb-2023] New preprint on efficient and robust generative models for EHRs. MedDiff
[Feb-2023] New preprint on domain adaptation for time series under feature and label shifts. Project Website
[Dec-2022] Thrilled to serve as the CHIL 2023 technology chair! Submit your papers by 2-15-2023.
[Oct-2022] We are orgnizing a mini-symposium, 'Optimization for Healthcare’, on SIAM Conference in Optimization 2023
[Oct-2022] We are orgnizing a mini-symposium, 'Acceleration methods for scientific and machine learning applications’, on SIAM Conference on Computational Science and Engineering 2023.
[Oct-2022] New preprint! We introduce an Efficient Nonlinear Acceleration method that Exploits Symmetry of the Hessian, addressing challenges and providing solutions for nonlinear acceleration.
[May-2022] “AUTM Flow: Atomic Unrestricted Time Machine for Monotonic Normalizing Flows” is accepted by UAI’22!
[Apr-2022] Defended my Ph.D. dissertation titled “Acceleration Algorithms for Machine Learning Models”!
[Jan-2022] “GDA-AM: Solving Minimax via Anderson Mixing” is accepted by ICLR’22!
About me
I am a postdoctoral fellow at University of Pennsylvania, working with Professor Chen Yong, Previously, I spent a year Harvard Medical School, working with Prof. Marinka Zitnik. I got my Ph.D. in Computer Science at Emory University, under the guidance of Dr. Yuanzhe Xi and Joyce Ho. My research interests lie primarily in machine learning, and span the entire theory-to-application spectrum from foundational advances all the way to deployment in real systems. Recently, I am working on numerical methods for accelerating large-scale models (e.g., tensor decomposition, deep generative models, neural networks).
Education
Ph.D. in Computer Science, Emory University, Aug. 2016 - May. 2022
M.S. in Financial Mathematics, University of Connecticut, Aug. 2014- Jun. 2016
B.S. in Financial Enginnering, Shanghai Finance University, Sept. 2010 - May. 2014
Research Focus
Statistical Machine Learning, Deep Learning, Graph Neural Network
Numerical Analysis, Iterative Algorithms, Optimization