Biography

I am a Research Scientist in the Applied Mathematics department at the University of Washington working with Nathan Kutz and Steve Brunton. My research involves data-driven discovery of dynamical systems, sparsity-promoting regularization methods in neural networks, and physics-informed anomaly detection. I have also worked on developing component-based reduced order models for parameter-dependent elliptic linear partial differential equations.

Interests

  • Machine Learning
  • Numerical Analysis
  • Scientific Computing
  • Reduced Order Modeling

Education

  • Ph.D. in Applied Mathematics (advanced data science option), 2020

    University of Washington

  • M.S. in Applied Mathematics, 2015

    University of Washington

  • B.S. in Applied Mathematics (specialization in computing), 2013

    University of California, Los Angeles

Experience

 
 
 
 
 

Software engineer intern

Facebook

Jun 2019 – Sep 2019 Seattle, WA

Detecting scam pages: I deployed three image-retrieval based models and trained a multi-channel page embedding for scam page detection.

Tools used:

  • K-nearest neighbors
  • Proprietary retrieval methods
  • Nonlinear embeddings
  • Convolutional and feedforward neural networks
  • SQL
 
 
 
 
 

Software engineer intern

Facebook

Jun 2018 – Sep 2018 Seattle, WA

Studying approaches for utilization of cross-domain data: I investigated different methods of incorporating cross-domain features into in-domain models.

Tools used:

  • Sparse nueral networks
  • Two-tower sparse neural networks
  • SQL

Software

PySINDy

PySINDy is an open source Python package Kathleen Champion and I created for the Sparse Identification of Nonlinear Dynamical systems (SINDy). We designed the package to make the process of learning governing equations from data as painless as possible for practitioners and to provide a standard implementation of the SINDy method for researchers to build upon.
Code Documentation Paper

Selected Coursework

  • Machine Learning (and Machine Learning for Big Data)
  • Numerical Linear Algebra
  • Numerical Solution of Differential Equations
  • Approximation Theory & Spectral Methods
  • Data visualization
  • Numerical Optimization
  • Dynamical Systems
  • Data Analysis
  • Statistics
  • Functional Analysis
  • Partial Differential Equations
  • Nonlinear Partial Differential Equations
  • Finite Volume Methods

Teaching

Instructor:


QuarterCourse
Autumn 2018AMATH 351: Introduction to Differential Equations and Applications
Summer 2017AMATH 351: Introduction to Differential Equations and Applications
Winter 2017AMATH 352: Applied Linear Algebra and Numerical Analysis
Summer 2016AMATH 352: Applied Linear Algebra and Numerical Analysis



Teaching Assistant:


QuarterCourse
Spring 2017AMATH 586: Graduate Numerical Anaylsis of Time Dependent Problems
Fall 2016AMATH 501: Graduate Vector Calculus and Complex Variables
Spring 2016MATH 126: Calculus III
Winter 2016MATH 125: Calculus II
Fall 2015AMATH 301: Beginning Scientific Computing
Spring 2015AMATH 301: Beginning Scientific Computing
Winter 2015MATH 124: Calculus I
Fall 2014MATH 124: Calculus I

Contact