Hi, I am Teresa

I am a data scientist passionate about representation learning, deep learning and interdisciplinary research. I enjoy telling stories with visualizations and using data science for social good. I am currently pursuing my PhD in Applied Mathematics and Statistics at Johns Hopkins University.

Interests

  • Representation Learning
  • Theory in Deep Learning
  • Interdisciplinary Research in Data Science

Education

  • Ph.D. in Applied Math & Stat, 2025

    Johns Hopkins University

  • M.S. in Data Science, 2020

    New York University

  • B.S. in Statistics and Economics, 2016

    University of Hong Kong

Research

Dimensionality reduction, regularization, and generalization in overparameterized regressions

We show how PCA avoids the peaking phenomenon of the double descent risk curve, and connect these results to adversarial attacks.

Learning Robust Multimodal Knowledge Graph Representations

We propose a new method to make NLP models more parameter efficient by storing and retrieving knowledge in an external knowledge graph.

A Simple Spectral Failure Mode for Graph Convolutional Networks

A simple generative model in which spectral graph embedding for subsequent inference succeeds whereas unsupervised GCN fails.

Adversarial attacks against linear and deep-learning regressions in astronomy

Our work generalizes adversarial attacks in regression settings and develops a comprehensive approach to measure attack success.

Projects

*

Autonomous driving

A CNN encoder-decoder model to navigate traffic environment using bird's eye view images.

Evaluating Ecosystem-climate Interactions in Eastern Africa

An interdisciplinary research project with Professor Sonali McDermid at the Department of Environmental Studies, NYU

Topic Modelling with Latent Dirichlet Allocation (LDA) on Wikipedia Articles

An interative visualization showing results of topic modelling on 33k Wikipedia articles

Chatbot

An interactive jupyter notebook implementing live chatbot using N-gram blocking

Matrix Completion for Different Missing Data Patterns

A study of three matrix imputation methods on different types of missing data patterns

Water Conservation

A data visualization showing global inequities of water usage and conservation suggestions

How Crypto Stacks Up Against Other Investments

A data-driven graphic story. Collaboration with Yue Qiu, Justina Lee and Adrian Leung in Bloomberg.