Ph.D. Candidate in Applied Mathematics
University of California, Merced
I develop statistics-informed neural-network surrogates for stochastic dynamical systems and hybrid simulation. My research interests include stochastic dynamical systems, scientific machine learning, uncertainty quantification, computational biology, and quantitative oncology.
Developing recurrent neural-network surrogates that learn and generate stochastic trajectories by matching marginal, cross-variable, temporal, and conditional statistics.
First-author manuscript in advanced preparation; submission expected late September or early October 2026.
Extending SINN through a branch–trunk architecture to reproduce distributions, time correlations, and parameter-conditioned statistics in quasi-stationary systems.
MDS26 poster and CSE27 invited talk.
Benchmarking neural-network architectures and numerical evaluation workflows for stochastic trajectory generation.
NCC26 poster planned. Final title and public repository forthcoming.
Embedded SINN as a neural surrogate for the fast stochastic component of a two-way coupled particle–continuum simulation and integrated generated trajectories into the multiscale workflow.
Ph.D. in Applied Mathematics, expected Spring 2027 · GPA: 4.00/4.00
Selected coursework: Scientific Computing and Deep Learning.
M.S. in Mathematical Finance
B.S. in Applied Mathematics: Actuarial Science
Certificate expected 2026. Completed: Bioinformatics Fundamentals (A+) and Genomic Sequencing Technologies (A).
Processing Actionable Data in Genomics and Modern-Omics: Technologies and Applications scheduled for Sep. 28–Nov. 27, 2026.
Cancer Genomics and Precision Oncology, in progress.