Biography

I am a Ph.D. student at University of Pennsylvania, where I am fortunate to be advised by Prof. René Vidal. My research interests broadly lie in problems that lie at the intersection of theory and practice in machine learning. Namely, I study problems where one can obtain provable guarantees for ML algorithms as well as demonstrate their efficacy in practice. A few particular areas of interest are adversarial robustness of deep networks, and inverse problems such as denoising corrupted signals by using deep generative models. I am an AWS-AI ASSET Fellow at UPenn for the year of 2024.

In the past, I have focused on trustworthy ML and adversarial robustness, studying the problem of provably reverse engineering adversarial attacks from corrupted samples. My recent focus is on studying the robustness of deep generative models and vision-language models to both adversarial and natural corruptions (such as camera or image corruptions).

I previously completed my MS in Computer Science at Columbia University, where I was advised by Prof. John Wright, and my BS degree in CS and Math at UT Austin.