teaching

I regard the opportunity to teach, mentor, and interact with students as the utmost privilege. As a statistician and data science educator, my teaching philosophy is to empower my students so that they can approach their pursuit of statistics with curiosity and confidence. Furthermore, I strive to reduce barriers to statistics and data science for all students, regardless of their previous mathematical background.

Below is a selected list of my teaching and mentoring experiences:

Johns Hopkins Bloomberg School of Public Health

• PH.140.850 - How to AI (for public health) (First Term 2025) - Course instructor
• 140.644 - Statistical Machine Learning (Term 4, 2025) - Course instructor (upcoming)

Project Supervisions at Johns Hopkins

• Can Wang (ScM Biostatistics -> PhD student, JHU Biostatistics).
  • Co-author on Evaluating Large Language Models for Evidence-Based Clinical Question Answering.
  • Co-author on InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI.
• Cathy Zhang (ScM Biostatistics -> PhD student, Columbia Biostatistics).
  • Full-text methods quality assessment with LLMs; co-author on Large Language Models for Full-Text Methods Assessment: A Case Study on Mediation Analysis.
  • Poster at IUS-NISS Conference on AI & Statistics 2025 supported by a Joseph Zeger Travel Award.
• Shengyi Li (ScM Biostatistics -> PhD student, Yale Statistics & Data Science).
  • Distributional matrix completion for gene perturbation prediction; poster at MLCB 2025 supported by a Joseph Zeger Travel Award.
  • Co-author on Power Analysis for Prediction-Powered Inference.
  • Co-author on Efficient Inference for Noisy LLM-as-a-Judge Evaluation.
• Moran Guo (ScM Biostatistics -> Biostatistician, LLX Solutions).
  • Prediction-powered inference for single-cell studies.
  • Co-author on Power Analysis for Prediction-Powered Inference.
  • Co-author on Efficient Inference for Noisy LLM-as-a-Judge Evaluation.
• Hongyu Zhao (BS/MS student, JHU Computer Science).
  • Co-author on InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI.
• Ivy (Junwei) Sun (student collaborator).
  • Co-author on Rethinking Perturbation Prediction Baselines, accepted to ICLR 2026 Gen2 Workshop.

Stanford University

• Effective Mentoring Practices Workshop

University of Washington

I have served as a Teaching Assistant for the following courses and have won an Outstanding Teaching Assistant Award in the School of Public Health at the University of Washington:

• Longitudinal Data Analysis (BIOSTAT 540; Graduate-level; Course rating: 4.7/5.0 (n = 47); Instructor: Katie Wilson)
• Categorical Data Analysis (BIOSTAT 536; Graduate-level; Instructor: Katie Kerr)
• Introductory Laboratory-Based Biostatistics (UCONJ 510; Graduate-level; Instructor: Lloyd Mancl)
• Machine Learning for Biomedical and Public Health Data (BIOSTAT 546; Graduate-level; Instructor: Daniela Witten)
• Summer Institute in Statistical Genetics (Instructors: Ken Rice & Ting Ye)
• Summer Institute in Statistics for Clinical & Epidemiological Research (Instructors: Katie Wilson & Anna Plantinga)

I’ve also given guest lectures and led weekly discussions in the following classes:

• Machine Learning for Biomedical and Public Health Data (BIOSTAT 546): Delivered guest lectures on decision trees, support vector machines, and principal component analysis.
• Categorical Data Analysis (BIOSTAT 536; Graduate level).

Mentor for the Directed Reading Program at University of Washington

• Mentored undergraduate students on topics of identification in missing data and causal inference.
• My mentee’s presentation is linked here.

Teaching Assistant at University of California, Berkeley

• Introduction to Machine Learning (CS 189/289A; Advanced undergraduate level; Fall 2016 & Spring 2017).
• Discrete Mathematics and Probability (CS 70; Undergraduate-level; Summer 2016 & Spring 2017).