I’m a Computer Science Ph.D. student at Princeton University.
I am fascinated by the interplay between machine learning, graphical models, causal inference, and computer vision. Recently I’ve been thinking about
Download my resumé.
Ph.D. candidate at Princeton University
B.S. in Computer Science with Honors and Specialization in Machine Learning & B.S. in Mathematics with Honors, 2022
The University of Chicago
High School Diploma in Science and Technology, 2018
Bahcesehir High School for Science and Technology
Introductory paper on Graphical Models and Causal Inference research with Bryon Aragam. We cover topics such as identifiability, Bayesian Networks, interventions, Structural Causal Models, etc.
Fast, scalable causal inference for time series using Representation Learning based on the GRAIL framework. The code is a link to the GRAIL framework that I wrote in Python and does not include the causal inference parts yet.
The final project for my Topological Data Analysis course. The idea is based on this paper that shows that the noise in GAN generated images can be reduced by introducing a topology layer. I show that this layer can also be integrated into cGANs and DCGANs and give better results on cGANs due to the possibility of specific loss functions.
An expository paper on modular forms where I prove that the space of modular forms can be orthogonally decomposed into the space of Eisenstein series and the space of cusp forms. Different aspects of modular forms are covered such as finite dimensionality, Hecke operators, and Petersson Inner Product.